© 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. 7815
    Prev
    Next
    INDEX
    Explanations

    of followed by nouns

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

    enumerated list items

    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
     tpr
    0.40
     Soder
    0.37
    نامج
    0.36
     Likes
    0.35
     SIA
    0.34
     tad
    0.34
    ☟
    0.34
     Roku
    0.34
     jit
    0.33
     Mile
    0.33
    POSITIVE LOGITS
    迠
    0.38
    sequently
    0.38
    ન્દ
    0.38
    whereas
    0.37
    MsgCallBack
    0.36
    ীশ
    0.35
    playerPosition
    0.35
    wohner
    0.35
    startTimestamp
    0.35
     extraordinarily
    0.34
    Activations Density 0.028%

    No Known Activations