© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3492
    Prev
    Next
    INDEX
    Explanations

    such as

    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_53_width_65k_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
    まさに
    0.46
    䐪
    0.45
     ちゃっ
    0.44
     اہلِ
    0.40
    ook
    0.38
    вели
    0.38
    👏👏
    0.36
    ниците
    0.36
    👏👏👏👏
    0.36
    முடிய
    0.36
    POSITIVE LOGITS
     such
    2.44
     เช่น
    2.41
    比如
    2.11
    such
    2.08
     таких
    2.00
     poput
    2.00
    例如
    1.99
     मसलन
    1.97
     مثل
    1.86
     такие
    1.84
    Activations Density 0.953%

    No Known Activations