© 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. 224790
    Prev
    Next
    INDEX
    Explanations

    surcharge, savings, owner

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

    spark curiosity, daughter of

    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
    -
    0.59
    (
    0.49
    :
    0.49
    Winter
    0.48
    ्यात
    0.47
    '
    0.47
     Winter
    0.46
    Show
    0.45
    udge
    0.44
    Stay
    0.44
    POSITIVE LOGITS
     kháng
    0.52
    が可能
    0.51
     tío
    0.50
     élevés
    0.50
    owner
    0.49
    getPrototypeOf
    0.47
    revoke
    0.47
     osob
    0.47
     করিয়৷
    0.46
    ophagus
    0.46
    Activations Density 0.000%

    No Known Activations