© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1515
    Prev
    Next
    INDEX
    Explanations

    blue whale

    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
     बच्‍
    0.23
     टीस्पून
    0.23
    descripcion
    0.22
    DebuggerNonUser
    0.22
    䏼
    0.22
    禣
    0.22
     ആണ്
    0.21
     monstru
    0.21
     연락
    0.21
    </bbox>
    0.20
    POSITIVE LOGITS
    -,
    0.31
    -
    0.29
    /
    0.29
    -/
    0.27
     /
    0.27
     or
    0.26
    ‐
    0.25
    _
    0.24
    ized
    0.23
     Walters
    0.21
    Activations Density 1.953%

    No Known Activations