© 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. 54012
    Prev
    Next
    INDEX
    Explanations

    you as soon as

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

    numbers aftertype claims intprice range

    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
    വിടെ
    0.49
     mercados
    0.49
    गौरतलब
    0.49
     परिचालन
    0.49
    ү
    0.49
    нить
    0.48
    顰
    0.48
     результа
    0.47
    蟳
    0.47
    inerja
    0.47
    POSITIVE LOGITS
     Wenn
    0.42
     >,
    0.42
    >?
    0.42
     monolithic
    0.41
    صميم
    0.41
     schema
    0.40
     和
    0.40
     Lorsque
    0.40
     type
    0.39
     >=
    0.39
    Activations Density 0.000%

    No Known Activations