© 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. 17598
    Prev
    Next
    INDEX
    Explanations

    in person or in-store

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

    in-

    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
     exaggeration
    0.38
     bedste
    0.37
     Places
    0.36
    놁
    0.36
    oleh
    0.35
    অন্যদিকে
    0.35
     anticip
    0.35
     indistinct
    0.35
    credible
    0.34
    ި
    0.34
    POSITIVE LOGITS
     vivo
    0.98
     situ
    0.92
    -
    0.92
    ־
    0.82
    ‐
    0.79
    ‑
    0.75
     vitro
    0.72
     person
    0.70
    person
    0.65
    -​
    0.64
    Activations Density 0.093%

    No Known Activations