© 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. 4900
    Prev
    Next
    INDEX
    Explanations

    describing a woman

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

    about something or someone

    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
     kori
    0.43
    endus
    0.41
    Meter
    0.41
     socks
    0.41
    捏
    0.41
     consentement
    0.40
    द्रोह
    0.40
     affrontare
    0.40
    otechnology
    0.40
     minu
    0.39
    POSITIVE LOGITS
     Child
    0.39
    TEMPLATE
    0.38
     облада
    0.37
     Rever
    0.36
    缥
    0.36
    WithName
    0.36
     በፍ
    0.36
     haw
    0.35
    AppBar
    0.35
     vaguely
    0.35
    Activations Density 0.000%

    No Known Activations