© 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. 2518
    Prev
    Next
    INDEX
    Explanations

    parameter or value separators

    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
    StoredKeys
    0.29
     ordained
    0.29
     Defts
    0.28
     newApproved
    0.27
    ㍍
    0.27
     fuelwood
    0.27
    แมนเชสเตอร์ซิตี
    0.27
     Elektrokh
    0.26
     Elektrokhimiya
    0.26
     phosphorylated
    0.26
    POSITIVE LOGITS
    ↵
    0.33
    is
    0.32
    state
    0.30
    custom
    0.30
    n
    0.30
    s
    0.29
    en
    0.29
    title
    0.29
    d
    0.29
    all
    0.29
    Activations Density 0.038%

    No Known Activations