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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35351
    Prev
    Next
    INDEX
    Explanations

    plan assessment opportunity details

    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
    kW
    0.93
    m
    0.85
    образ
    0.84
    বার
    0.80
     виде
    0.78
     trois
    0.78
    pi
    0.78
    align
    0.77
    𝐢
    0.77
     empêcher
    0.76
    POSITIVE LOGITS
     warehousing
    0.73
    蛐
    0.73
     marred
    0.72
     fraudulent
    0.72
    衅
    0.71
    玝
    0.70
    েও
    0.70
     detrimental
    0.70
     Activities
    0.69
     your
    0.69
    Activations Density 0.000%

    No Known Activations