© 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. 195305
    Prev
    Next
    INDEX
    Explanations

    updating policies or specifications

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

    unlocks insight

    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
     gevallen
    0.48
     (
    0.43
     Louis
    0.43
     Sachen
    0.42
    therapeutic
    0.42
     Leopard
    0.42
    icious
    0.41
    undu
    0.41
     Dub
    0.40
     Pur
    0.40
    POSITIVE LOGITS
     CHANGES
    0.51
     पाओ
    0.50
     analisis
    0.49
     analis
    0.49
    ༸
    0.48
     psicologia
    0.48
    ҽ
    0.48
     ANALYSIS
    0.47
    ɳ
    0.47
    лм
    0.46
    Activations Density 0.001%

    No Known Activations