© 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. 2406
    Prev
    Next
    INDEX
    Explanations

    notes and addenda

    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
     মর্টার
    0.19
    Usuarios
    0.18
    ાઇલ
    0.18
     kammam
    0.18
    㞓
    0.18
    Introduceti
    0.18
    barui
    0.18
    <unused2022>
    0.18
     natthi
    0.18
    ཊ
    0.18
    POSITIVE LOGITS
    .)
    0.25
     ii
    0.24
    .,
    0.23
     iii
    0.22
    .(
    0.22
    )...
    0.21
    iiii
    0.21
    iii
    0.21
    ,(
    0.20
    /
    0.20
    Activations Density 0.181%

    No Known Activations