© 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. 79064
    Prev
    Next
    INDEX
    Explanations

    descriptive nouns and events

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

    safety and view

    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
     tacos
    0.48
     macOS
    0.45
     definite
    0.45
     DSS
    0.44
     DCP
    0.44
    *
    0.44
     countertop
    0.43
     approx
    0.43
     COP
    0.43
     PATH
    0.43
    POSITIVE LOGITS
    V
    0.57
    를
    0.53
    자
    0.53
    ור
    0.52
    汜
    0.51
    Giải
    0.51
    പ
    0.51
    ল
    0.50
    로
    0.50
     potrzeby
    0.50
    Activations Density 0.000%

    No Known Activations