© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4095
    Prev
    Next
    INDEX
    Explanations

    cave criticism piracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    เหล่านี้
    1.78
    7
    1.76
     Gabri
    1.73
     minecraft
    1.68
    irrit
    1.68
    Cellphone
    1.66
    6
    1.66
    <unused1697>
    1.65
    8
    1.65
     sdf
    1.63
    POSITIVE LOGITS
     an
    1.20
     the
    1.16
     a
    1.08
    vester
    1.00
    しの
    0.96
    ungan
    0.92
    the
    0.91
     oan
    0.91
     one
    0.88
     Removal
    0.88
    Activations Density 0.097%

    No Known Activations