© 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. 164188
    Prev
    Next
    INDEX
    Explanations

    business transactions and details

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

    from whence all, egg circle

    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
    layered
    0.52
    drav
    0.49
    mathemat
    0.48
    igues
    0.46
    lit
    0.46
     skirm
    0.46
    verson
    0.45
    r
    0.45
    ders
    0.45
    ről
    0.45
    POSITIVE LOGITS
     потери
    0.56
     circunstancias
    0.53
    CUR
    0.50
     dėl
    0.49
    GAAP
    0.49
    CE
    0.48
     cabello
    0.48
    OH
    0.47
    WS
    0.47
    HK
    0.47
    Activations Density 0.000%

    No Known Activations