© 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. 116718
    Prev
    Next
    INDEX
    Explanations

    origin or current state

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

    current state or position

    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
     rencont
    0.54
     அங்கு
    0.53
     όπου
    0.53
     అక్కడ
    0.52
     erforderlich
    0.49
     indiquée
    0.49
     곳
    0.49
     шесть
    0.49
     exercer
    0.48
     действует
    0.47
    POSITIVE LOGITS
     from
    0.56
    0.53
    i
    0.53
     tone
    0.52
     To
    0.51
    from
    0.49
     turnt
    0.47
    coming
    0.47
    e
    0.46
     The
    0.46
    Activations Density 0.049%

    No Known Activations