© 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. 4828
    Prev
    Next
    INDEX
    Explanations

    van der

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

    names, acronyms, and phone numbers

    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
     yıl
    0.42
     generell
    0.42
     wenigen
    0.41
     enfim
    0.40
     సమీ
    0.39
     []);
    0.39
     slij
    0.39
     geri
    0.39
     hatta
    0.39
     baseApiPath
    0.39
    POSITIVE LOGITS
     RB
    0.51
    RZ
    0.49
    Rp
    0.48
    RJ
    0.47
    RB
    0.47
    RCB
    0.45
    ԝ
    0.43
    Rb
    0.43
     ಆರ್
    0.43
     RR
    0.41
    Activations Density 0.243%

    No Known Activations