© 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. 159545
    Prev
    Next
    INDEX
    Explanations

    connecting phrases and clauses

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

    rabbit population, events, modeling

    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
     verk
    0.46
    ن
    0.44
    وا
    0.43
    При
    0.42
     adı
    0.42
    ಸ್
    0.42
     if
    0.42
    저
    0.42
     मनोर
    0.41
    verw
    0.41
    POSITIVE LOGITS
    ）。
    0.42
     দিলো
    0.42
     নিয়মিত
    0.41
    },"
    0.41
     pleinement
    0.41
    clu
    0.40
     Trib
    0.40
    ürnberg
    0.39
    মায়
    0.39
    aughlin
    0.39
    Activations Density 0.000%

    No Known Activations