© 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. 111978
    Prev
    Next
    INDEX
    Explanations

    growth rates

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

    repeat or continuation

    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
     जल
    0.43
    спект
    0.43
    是怎么
    0.42
     =",
    0.42
    titleMargin
    0.41
    필
    0.40
    싶
    0.40
    푠
    0.40
    ㅣ
    0.40
    뭔
    0.40
    POSITIVE LOGITS
    kina
    0.48
     russe
    0.47
     Rusia
    0.46
    ියාව
    0.46
    धपुर
    0.46
     blandt
    0.45
     venezolano
    0.44
     agosto
    0.43
     ulang
    0.43
     கொண்டுள்ளது
    0.43
    Activations Density 0.001%

    No Known Activations