© 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. 9526
    Prev
    Next
    INDEX
    Explanations

    with them

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

    "ID" explanations or definitions

    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
    ,
    0.57
     –
    0.56
    t
    0.53
     >>
    0.50
     ‘
    0.48
    …
    0.46
     (
    0.46
     -
    0.44
    pes
    0.44
     …
    0.43
    POSITIVE LOGITS
     mignon
    0.56
    Prothorax
    0.53
    蹼
    0.53
    唳
    0.51
    लट्
    0.51
    齙
    0.50
     radii
    0.49
    لو
    0.49
    हेलो
    0.48
     ciekaw
    0.48
    Activations Density 0.000%

    No Known Activations