© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5678
    Prev
    Next
    INDEX
    Explanations

    console.log

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
     hitting
    0.64
    ModuleName
    0.63
    ভেট
    0.63
     casket
    0.63
     templateUrl
    0.60
    হতের
    0.59
     చెందిన
    0.59
    ص
    0.58
    صد
    0.58
    osen
    0.58
    POSITIVE LOGITS
     logon
    0.84
    DIFF
    0.80
    찜
    0.79
     XOR
    0.79
    log
    0.78
     Anal
    0.77
     amph
    0.76
     anal
    0.73
    恆
    0.72
     Analog
    0.72
    Activations Density 0.063%

    No Known Activations