© 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. 307
    Prev
    Next
    INDEX
    Explanations

    cities, planets, groups, places

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

    names followed by punctuation

    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
    8
    0.47
    6
    0.40
     apps
    0.40
     های
    0.39
     spectra
    0.38
     of
    0.38
    7
    0.38
     off
    0.38
     iPad
    0.37
    4
    0.37
    POSITIVE LOGITS
    whose
    0.50
    ®.
    0.48
     ซึ่ง
    0.47
    ซึ่ง
    0.47
    。
    0.46
     અને
    0.45
    although
    0.45
    ։
    0.45
    which
    0.44
    ،
    0.44
    Activations Density 0.181%

    No Known Activations