© 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. 178848
    Prev
    Next
    INDEX
    Explanations

    Street or specific concepts

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

    status regarding

    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
     Evaluating
    0.51
    బ్బు
    0.45
     Conditions
    0.44
    ش
    0.44
    产权
    0.43
    ండి
    0.43
     Locks
    0.43
     diagonalization
    0.43
    ާމ
    0.42
    ب
    0.41
    POSITIVE LOGITS
    ǰ
    0.49
     ανθ
    0.49
     curtailed
    0.49
    тый
    0.48
     majest
    0.47
     acrob
    0.46
     circumst
    0.46
     impressively
    0.46
    ਝ
    0.46
     огром
    0.46
    Activations Density 0.000%

    No Known Activations