© 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. 4737
    Prev
    Next
    INDEX
    Explanations

    man-made

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

    human, beings

    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
    ంప
    0.44
    ધી
    0.43
    چی
    0.42
    delicious
    0.41
     терми
    0.40
    ᱨ
    0.40
    𒄑
    0.39
     но
    0.39
    酽
    0.39
    കർ
    0.38
    POSITIVE LOGITS
     beings
    0.92
    hattan
    0.90
    ifold
    0.80
    atee
    0.77
    ifolds
    0.70
    itarian
    0.69
    hood
    0.67
    liness
    0.67
    ufact
    0.66
    made
    0.66
    Activations Density 0.086%

    No Known Activations