© 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. 5658
    Prev
    Next
    INDEX
    Explanations

    did you

    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
     me
    0.68
    centred
    0.67
    ღ
    0.66
    ẫn
    0.65
    كمان
    0.64
     nền
    0.64
    plica
    0.64
    ⑅
    0.64
     পঞ্চাশ
    0.63
    Sales
    0.63
    POSITIVE LOGITS
     अपने
    0.93
     अपना
    0.77
     ও
    0.66
    ของ
    0.64
     अपनी
    0.63
    तंत्र
    0.62
     programming
    0.61
    ையின்
    0.61
     के
    0.61
     ili
    0.61
    Activations Density 0.009%

    No Known Activations