© 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. 22821
    Prev
    Next
    INDEX
    Explanations

    financial exchange or rates

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

    mathematical operations and logic

    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
    count
    0.47
    al
    0.46
    key
    0.44
    p
    0.44
    aso
    0.43
     how
    0.41
    cial
    0.41
    api
    0.40
    day
    0.40
    how
    0.40
    POSITIVE LOGITS
     añadir
    0.47
    幵
    0.46
     單
    0.45
     generación
    0.45
     comentar
    0.45
     protegido
    0.45
    大战
    0.44
     অর্চন
    0.44
     femelles
    0.43
     desech
    0.43
    Activations Density 0.000%

    No Known Activations