© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4353
    Prev
    Next
    INDEX
    Explanations

    evidence of harm. * **Also Necessary (for custody):** Evidence of the child's best interests – this could be proof of stability, financial resources, parental involvement, and (in cases of abuse)títulos en física y economía de la Universidad de Pensilvania. **Empresas principales:** * **PayPalcharter.proof of purchase. We need to see if your device is still under warranty. We have checked your charger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ،
    0.85
    ுக
    0.84
     sanctity
    0.75
    ,
    0.73
     fixé
    0.73
    會有
    0.71
     conviene
    0.71
    :
    0.71
     fleste
    0.70
    기간
    0.70
    POSITIVE LOGITS
    the
    1.18
     а
    1.06
    𝚊
    1.00
    al
    0.98
    an
    0.97
    нг
    0.93
     the
    0.93
    𝚜
    0.91
    it
    0.90
    ке
    0.89
    Activations Density 0.000%

    No Known Activations