© 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. 3231
    Prev
    Next
    INDEX
    Explanations

    the followed by a word

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

    the followed by descriptive nouns

    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
    的三
    0.20
    represents
    0.20
    ⴳ
    0.19
    idespread
    0.19
     područ
    0.18
    inguistic
    0.18
     whose
    0.18
     miljoen
    0.18
    🏞
    0.18
     مدينة
    0.18
    POSITIVE LOGITS
     guy
    0.22
     only
    0.22
     onus
    0.22
     it
    0.21
     funniest
    0.20
     guys
    0.20
    я
    0.19
     μόνο
    0.19
     только
    0.19
    ses
    0.19
    Activations Density 0.900%

    No Known Activations