© 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. 1992
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by numbers or letters

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

    parentheses followed by bold markdown

    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
     kuid
    0.41
     isto
    0.38
     illo
    0.37
    .*/
    0.37
     ק
    0.36
     slic
    0.35
     aki
    0.35
     snd
    0.35
     niet
    0.34
     promin
    0.34
    POSITIVE LOGITS
    ؓ
    0.32
     Espero
    0.28
    “[
    0.28
    घाटन
    0.27
    "[
    0.27
    जैसे
    0.27
     practicable
    0.26
     परामर्श
    0.26
     imaginative
    0.26
    Дата
    0.26
    Activations Density 0.421%

    No Known Activations