© 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. 5714
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by punctuation

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

    LLMs, NLP, CSF

    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
     ૨
    0.44
     esfuerzos
    0.42
     nuovamente
    0.42
    χου
    0.39
    сима
    0.38
    လ်
    0.38
    ম্ম
    0.38
    ल्शियम
    0.37
    UpdateChoice
    0.37
    ²',
    0.37
    POSITIVE LOGITS
    Fig
    0.40
    推定
    0.38
    "`
    0.38
    Lem
    0.38
    ここに
    0.37
     belonging
    0.37
    ここで
    0.36
     incapac
    0.36
     aftermath
    0.36
    ?;
    0.36
    Activations Density 0.029%

    No Known Activations