© 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. 8296
    Prev
    Next
    INDEX
    Explanations

    future possibility or advice

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

    Here's a breakdown

    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
    饭
    0.37
    𝐢
    0.37
     Gleich
    0.36
    ミルク
    0.35
    )?;
    0.34
    %%%%%%%%%%%%%
    0.34
    ('-');
    0.34
    珺
    0.34
    はじめ
    0.34
     Weir
    0.34
    POSITIVE LOGITS
     nk
    0.48
     arreg
    0.46
     scheda
    0.44
     cres
    0.42
    τες
    0.42
     रेसि
    0.40
    বিত
    0.39
     에게
    0.38
     arguments
    0.38
    Tk
    0.38
    Activations Density 0.016%

    No Known Activations