© 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. 2099
    Prev
    Next
    INDEX
    Explanations

    names following titles or first names

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

    Jang Woo-yeong, Sarah Mink

    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
    -
    0.30
    1
    0.29
    #
    0.29
     F
    0.28
    %
    0.28
    0
    0.27
     Mexican
    0.27
     B
    0.26
    F
    0.26
     N
    0.25
    POSITIVE LOGITS
    <unused429>
    0.31
     kellett
    0.30
    <unused1049>
    0.29
     simonsen
    0.28
     realidade
    0.28
    <unused2046>
    0.28
     réalité
    0.27
    <unused401>
    0.27
     diretta
    0.27
    <unused610>
    0.27
    Activations Density 0.248%

    No Known Activations