© 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. 66454
    Prev
    Next
    INDEX
    Explanations

    capacity to lift, ride, or buy

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

    specific nouns and technical terms

    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
     Interest
    0.42
    ಗಳನ್ನು
    0.42
     Particular
    0.42
     Their
    0.40
     Conditioning
    0.40
     Pieces
    0.39
     ，
    0.39
     audi
    0.38
    ativamente
    0.38
     Maka
    0.38
    POSITIVE LOGITS
    運び
    0.46
    hij
    0.44
     উপার্জন
    0.44
    ôtel
    0.43
    しゃれ
    0.43
    ückt
    0.42
    ིན་
    0.42
     чтобы
    0.42
    ᖕ
    0.42
    でお
    0.42
    Activations Density 0.002%

    No Known Activations