© 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. 1337
    Prev
    Next
    INDEX
    Explanations

    block followed by numbers

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

    numbers containing 9

    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
    ᱔
    0.46
    <0x91>
    0.43
     ۶
    0.38
    ４
    0.38
    ெய்
    0.37
     ৪
    0.36
     ২২
    0.36
    ၎
    0.36
     ۴
    0.36
     ২০১৯
    0.35
    POSITIVE LOGITS
    xxx
    0.45
    0.40
    的情
    0.39
     chị
    0.39
    XXX
    0.38
     পরের
    0.36
     Vast
    0.35
    int
    0.35
    xxxx
    0.35
     Lein
    0.35
    Activations Density 0.318%

    No Known Activations