© 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. 153671
    Prev
    Next
    INDEX
    Explanations

    services types fighters walker

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

    discussing specific entities / actions

    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
    焓
    0.48
     kush
    0.46
    лько
    0.44
     eneste
    0.44
     spate
    0.43
     ạ
    0.42
     einzige
    0.42
     luxe
    0.42
    莽
    0.42
     wap
    0.42
    POSITIVE LOGITS
    lifecycle
    0.49
    excellence
    0.47
    foundation
    0.45
    azes
    0.45
    interacting
    0.44
    ंपूर्वी
    0.43
    addition
    0.43
     groundwork
    0.43
     উৎকৃষ্ট
    0.43
    founder
    0.43
    Activations Density 0.000%

    No Known Activations