© 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. 1584
    Prev
    Next
    INDEX
    Explanations

    `Dar` names

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

    my safety guidelines and programming

    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
     జ
    0.36
    chema
    0.36
    MaxScaler
    0.35
    స్తూ
    0.34
     jato
    0.34
    isins
    0.34
     جول
    0.33
     шам
    0.33
    瓜
    0.33
     InputStream
    0.33
    POSITIVE LOGITS
     Darby
    0.41
    Dar
    0.39
    dar
    0.39
     Darling
    0.38
    Curly
    0.37
     Dar
    0.36
    Louis
    0.36
    ándor
    0.36
    Bun
    0.36
    อัต
    0.36
    Activations Density 0.037%

    No Known Activations