© 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. 2614
    Prev
    Next
    INDEX
    Explanations

    your. B, 2, ’

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

    acts like a model

    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
     聞い
    0.33
     États
    0.32
    clampsia
    0.32
     immunological
    0.31
     ставкалары
    0.31
     `${
    0.31
     উত্তরে
    0.31
    ériques
    0.31
     Jahrhund
    0.31
     jurid
    0.30
    POSITIVE LOGITS
    Our
    0.47
    M
    0.46
    Mega
    0.46
    We
    0.46
    My
    0.46
    MS
    0.45
    Super
    0.42
    Simple
    0.42
    P
    0.41
    PRO
    0.41
    Activations Density 0.163%

    No Known Activations