© 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. 67229
    Prev
    Next
    INDEX
    Explanations

    clear vinyl, deer, orchards, potato, families, writing

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

    Enhanced Cognitive

    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
    ও
    0.50
     एलान
    0.49
     関係
    0.49
     ऐलान
    0.49
    亀
    0.49
     スタ
    0.46
     proclamation
    0.46
     ঘোষণা
    0.46
     જણ
    0.46
    スケジュール
    0.46
    POSITIVE LOGITS
    ut
    0.48
    h
    0.48
    opot
    0.45
    খিক
    0.44
    asel
    0.43
    ~$
    0.42
    更高
    0.42
    angaroo
    0.42
    امية
    0.41
    brero
    0.41
    Activations Density 0.000%

    No Known Activations