© 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. 151881
    Prev
    Next
    INDEX
    Explanations

    new year, guess upon

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

    foul language and controversial responses

    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
    ENN
    0.47
    FORT
    0.44
    ZI
    0.43
    IGHT
    0.42
    טה
    0.42
    久
    0.42
     pary
    0.41
    COLOG
    0.41
    UN
    0.40
    ボリー
    0.39
    POSITIVE LOGITS
     similaires
    0.46
    ន្ថ
    0.44
     symbolName
    0.44
     এটাই
    0.43
     zásobníku
    0.43
    ান্ডের
    0.43
     दख
    0.43
     এখান
    0.42
     speechSynthesis
    0.42
     />}
    0.42
    Activations Density 0.001%

    No Known Activations