© 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. 47180
    Prev
    Next
    INDEX
    Explanations

    during winter

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

    explain dice, SPI, -v

    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
    データベース
    0.50
    사이트
    0.43
    PutMapping
    0.43
     grounds
    0.43
     পুরোপুরি
    0.42
    ﯿ
    0.42
    يذ
    0.42
     soltanto
    0.42
     esimerkiksi
    0.42
    บริเวณ
    0.41
    POSITIVE LOGITS
     Childhood
    0.45
     During
    0.44
     família
    0.42
     Communicate
    0.41
     Variants
    0.41
     baixar
    0.40
     từ
    0.40
     Heather
    0.40
    ):
    0.39
     familias
    0.39
    Activations Density 0.000%

    No Known Activations