© 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. 3744
    Prev
    Next
    INDEX
    Explanations

    file extensions with wildcards

    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
    َ
    1.48
    ל
    1.41
    ز
    1.36
    entric
    1.35
    eworthy
    1.32
    ere
    1.27
    CIAL
    1.25
    Mga
    1.20
    gru
    1.19
    י
    1.18
    POSITIVE LOGITS
    an
    1.30
    ்ப்பு
    1.18
     variés
    1.14
    u
    1.14
    িয়ান
    1.13
     ЕГЭ
    1.13
     problemat
    1.13
    जूद
    1.12
    timeInterval
    1.12
     dusted
    1.12
    Activations Density 0.017%

    No Known Activations