© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246776
    Prev
    Next
    INDEX
    Explanations

    specific instances or parts

    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
    Negative Logits
    亥
    0.52
    <0x0D>
    0.46
     ContentValues
    0.46
     lament
    0.45
    ナソニック
    0.45
    ués
    0.44
     quebr
    0.43
    틱
    0.42
     nächsten
    0.42
    ſe
    0.42
    POSITIVE LOGITS
    selecting
    0.52
    operate
    0.51
     operates
    0.50
    array
    0.46
     функциони
    0.45
     வேலை
    0.45
     operasi
    0.44
    depends
    0.44
     from
    0.44
    about
    0.43
    Activations Density 0.001%

    No Known Activations