© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7613
    Prev
    Next
    INDEX
    Explanations

    across tabs, gaps, remain

    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_31_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
     எனது
    0.77
    }(
    0.74
    랍
    0.74
    }\
    0.73
    Spanish
    0.73
    }"
    0.73
    ức
    0.70
     जोड़
    0.70
    pilot
    0.66
    }$
    0.66
    POSITIVE LOGITS
     weren
    0.83
     were
    0.78
     remained
    0.77
    ंगामा
    0.76
     recalcul
    0.75
    сами
    0.73
     are
    0.73
    ເພດ
    0.73
    hne
    0.72
    ະພັນ
    0.71
    Activations Density 0.000%

    No Known Activations