© 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. 53179
    Prev
    Next
    INDEX
    Explanations

    line then

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

    transaction, database, limit

    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
    MutableArray
    0.47
     স্থান
    0.42
     〢
    0.42
     Dorado
    0.42
    ண்ப
    0.42
     লোকে
    0.42
    桻
    0.42
     急
    0.41
    wheres
    0.41
    は約
    0.40
    POSITIVE LOGITS
    ati
    0.52
     disimpan
    0.50
    ించడానికి
    0.50
    processes
    0.49
     carreg
    0.48
     adiab
    0.48
     최대한
    0.47
     transcription
    0.46
     일반적으로
    0.46
    oras
    0.46
    Activations Density 0.000%

    No Known Activations