© 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. 1362
    Prev
    Next
    INDEX
    Explanations

    names or numbers followed by text

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

    a fix

    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
    りが
    0.32
    <unused61>
    0.30
    )=\
    0.29
    数が
    0.28
     riguard
    0.28
    ufficient
    0.28
    marshalN
    0.27
    )\
    0.27
    )|$(
    0.27
    zahlen
    0.27
    POSITIVE LOGITS
     Robert
    0.37
     David
    0.35
     Richard
    0.35
     John
    0.35
    Robert
    0.34
     ESPN
    0.33
     Michael
    0.33
     Jonathan
    0.33
     billionaire
    0.31
    Richard
    0.31
    Activations Density 0.244%

    No Known Activations