© 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. 32891
    Prev
    Next
    INDEX
    Explanations

    punctuation and common words

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

    Presidents' Day dataset

    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
    '
    0.46
     cyclopent
    0.42
     .
    0.39
    icum
    0.39
     نشان
    0.39
     commotion
    0.38
    '].
    0.38
    任何
    0.38
     നിര
    0.38
    illas
    0.37
    POSITIVE LOGITS
    қта
    0.51
    ცია
    0.48
    밂
    0.47
    𝘔
    0.47
    zać
    0.46
    רת
    0.46
    involved
    0.46
    খিক
    0.46
     있지만
    0.45
    חנו
    0.45
    Activations Density 0.001%

    No Known Activations