© 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. 1809
    Prev
    Next
    INDEX
    Explanations

    multiplication table

    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
    Pada
    0.42
    ukkh
    0.42
    律师
    0.39
    Hemos
    0.39
    Excluded
    0.37
    Thoreau
    0.37
    皤
    0.37
    RAchievement
    0.36
    निर
    0.36
    Baer
    0.36
    POSITIVE LOGITS
     Future
    0.40
     quals
    0.38
     Ј
    0.38
    ↵
    0.37
     G
    0.37
     Simply
    0.37
     Going
    0.37
     ৫৭
    0.37
     Defence
    0.36
     Stim
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.