© 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. 46095
    Prev
    Next
    INDEX
    Explanations

    foreign language content

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

    domain names

    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
    3
    0.52
    2
    0.50
     messy
    0.49
     forest
    0.48
     lumber
    0.46
     gamer
    0.45
    forest
    0.45
     forestry
    0.44
     drummer
    0.44
     नागल
    0.44
    POSITIVE LOGITS
     pratiquer
    0.54
    ]^
    0.50
    ท่าน
    0.50
    currentComponent
    0.50
     שא
    0.49
     νό
    0.47
     虽然
    0.47
     trattano
    0.47
     preciso
    0.46
     xâm
    0.46
    Activations Density 0.000%

    No Known Activations