© 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. 9220
    Prev
    Next
    INDEX
    Explanations

    want to / used to

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

    programming code or specific tasks

    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
    guas
    0.49
     હજાર
    0.45
    TestSource
    0.45
     BSData
    0.43
     Opportunity
    0.43
     অপ
    0.42
     Counts
    0.41
    Ὀ
    0.41
     اسک
    0.41
    မှု
    0.40
    POSITIVE LOGITS
    と同じ
    0.46
    coded
    0.45
     공연
    0.45
     ਕੀ
    0.44
     г
    0.42
     মনির
    0.41
     deployments
    0.40
     rehearsals
    0.39
     closures
    0.39
     }}\
    0.39
    Activations Density 0.000%

    No Known Activations