© 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. 2290
    Prev
    Next
    INDEX
    Explanations

    change or withdrawal

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

    Geek Squad, potential victims, molecules, Cuba

    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
     hydrates
    0.41
     fire
    0.39
    pidos
    0.38
     hyd
    0.38
     coughing
    0.37
    Gul
    0.37
     complaint
    0.37
    他
    0.37
    Fire
    0.36
    apolitan
    0.36
    POSITIVE LOGITS
    Jimmy
    1.05
     Jimmy
    1.04
     Acet
    0.58
     round
    0.57
     JIM
    0.54
     ROUND
    0.52
    round
    0.51
    Round
    0.50
     acet
    0.50
    Acet
    0.50
    Activations Density 0.000%

    No Known Activations