© 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. 28845
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific terms

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

    Lord, legal, Twitter, programs, repetition

    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
     vidrio
    0.47
     porcentaje
    0.43
    тное
    0.42
     стекла
    0.42
    AMT
    0.41
     포인트
    0.41
    Wal
    0.40
    c
    0.40
    cello
    0.39
     chegar
    0.39
    POSITIVE LOGITS
     تاکہ
    0.52
    今日も
    0.51
     retardation
    0.48
     pathophys
    0.47
    kprop
    0.46
    ᕆ
    0.46
    ᑦ
    0.45
    promoting
    0.45
    เพื่อให้
    0.45
    ᅱ
    0.45
    Activations Density 0.000%

    No Known Activations