© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15858
    Prev
    Next
    INDEX
    Explanations

    the followed by nouns

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

    Petronas Twin Towers

    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_31_width_262k_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
    ור
    0.52
    st
    0.47
    tt
    0.46
    儘
    0.45
    >[]
    0.45
    ;
    0.45
     sloppy
    0.43
    I
    0.43
    ል
    0.43
     möglichst
    0.43
    POSITIVE LOGITS
     ಸುಮ
    0.50
     पोहो
    0.50
     deixou
    0.49
     Акча
    0.49
     फैशन
    0.49
     پیسے
    0.48
     Positive
    0.48
     देऊ
    0.48
     União
    0.47
     نکال
    0.46
    Activations Density 0.000%

    No Known Activations