© 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. 34308
    Prev
    Next
    INDEX
    Explanations

    within numbers

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

    documentation and explanation

    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
     overpriced
    0.50
     persone
    0.50
     Berc
    0.48
     vond
    0.47
     ate
    0.46
     Bonner
    0.46
     audiencia
    0.46
    ’
    0.46
     nie
    0.45
     transcend
    0.45
    POSITIVE LOGITS
    CreateWall
    0.46
    Photography
    0.46
     ప్రో
    0.45
    үз
    0.45
     బంగ
    0.45
    CAMERA
    0.44
     Photography
    0.44
    Documentation
    0.44
    ofluorescence
    0.44
    Description
    0.44
    Activations Density 0.000%

    No Known Activations