© 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. 41123
    Prev
    Next
    INDEX
    Explanations

    mother-in-law, brother-in-law, sister-in-law

    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
    er
    1.04
    にっいて
    0.98
    ১৭
    0.96
     seu
    0.96
     njegove
    0.95
    на
    0.94
    с
    0.94
    帙
    0.94
    也许
    0.91
     suas
    0.90
    POSITIVE LOGITS
    ︎
    0.97
    AGE
    0.96
    shine
    0.93
    gather
    0.91
    ONE
    0.89
    sail
    0.89
    padding
    0.89
     zirconia
    0.89
    деся
    0.89
    Count
    0.89
    Activations Density 0.010%

    No Known Activations