© 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. 212300
    Prev
    Next
    INDEX
    Explanations

    specific names and places

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

    created you, collaborative novel, allergic to

    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
    ⋘
    0.57
     lipoproteins
    0.57
    ަ
    0.53
    LAST
    0.52
    ROOM
    0.51
    шко
    0.50
     Gans
    0.50
    REQUIRED
    0.50
     currentLocation
    0.50
    瑀
    0.49
    POSITIVE LOGITS
    ế
    0.45
     mention
    0.45
     nhá
    0.45
     حض
    0.44
     जानिए
    0.43
    pt
    0.43
    amb
    0.43
     बंध
    0.43
    uteur
    0.42
     communion
    0.42
    Activations Density 0.000%

    No Known Activations