© 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. 156430
    Prev
    Next
    INDEX
    Explanations

    exposé and disclosure

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

    Apples, symptom

    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
     Führung
    0.44
    ak
    0.43
    instit
    0.42
    is
    0.42
    t
    0.42
     żad
    0.42
    st
    0.41
     아주
    0.41
    ht
    0.41
    getJSON
    0.41
    POSITIVE LOGITS
    Reconnect
    0.52
    Cuando
    0.51
    Ω
    0.48
    When
    0.47
    Rib
    0.44
     expose
    0.44
    बरे
    0.43
     disclosure
    0.42
    Locations
    0.42
     exposé
    0.42
    Activations Density 0.001%

    No Known Activations