© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2808
    Prev
    Next
    INDEX
    Explanations

    .

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

    code comments and session data

    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
    னால
    0.44
     هفت
    0.40
    rétaire
    0.38
    ტიკ
    0.37
    ట్స్‌మన్
    0.37
     (**
    0.36
    ಲಾಯಿತು
    0.36
    |<\
    0.36
     Regents
    0.36
    ه‌
    0.36
    POSITIVE LOGITS
    //
    0.55
     //
    0.53
     ///
    0.47
    console
    0.46
     console
    0.45
     //=>
    0.44
    fot
    0.43
    ㅁ
    0.43
     ----
    0.43
    mak
    0.42
    Activations Density 0.001%

    No Known Activations