© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209342
    Prev
    Next
    INDEX
    Explanations

    times and majority

    np_acts-logits-general · gemini-2.5-flash-lite

    meeting minutes and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cmb
    0.57
    haal
    0.49
    বৈশাখ
    0.49
    oló
    0.45
    ನ್ಸ್
    0.45
    バリ
    0.45
    జయ
    0.45
    羹
    0.45
    amek
    0.44
     үч
    0.43
    POSITIVE LOGITS
    Therefore
    0.61
     of
    0.49
     Therefore
    0.46
    ல்ல
    0.45
     ،
    0.44
     Hospital
    0.44
    ِ
    0.44
    Thank
    0.44
    Payment
    0.43
    Credit
    0.43
    Activations Density 0.000%

    No Known Activations