© 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. 163116
    Prev
    Next
    INDEX
    Explanations

    pretty close

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

    how are you

    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
    Vanilla
    0.52
    없는
    0.50
    脛
    0.49
    從小
    0.48
    倉
    0.47
    𝓗
    0.47
    層
    0.46
    ሱስ
    0.46
    但在
    0.45
    স্বপ
    0.45
    POSITIVE LOGITS
     to
    0.50
     Informatics
    0.49
     elucidation
    0.47
     informatics
    0.47
     speł
    0.45
     elucid
    0.45
     acquitted
    0.44
     frank
    0.44
     abode
    0.43
     reissue
    0.43
    Activations Density 0.000%

    No Known Activations