© 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. 222727
    Prev
    Next
    INDEX
    Explanations

    transmitters carrying, wasting the, a winner, personal sites, choose between, fifteen steps

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

    about building intimacy or exploring power dynamics

    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
     observa
    0.53
    <start_of_image>
    0.52
    '
    0.51
     forem
    0.50
     conjunto
    0.50
     allege
    0.49
     verb
    0.48
     field
    0.48
     developer
    0.48
     mark
    0.47
    POSITIVE LOGITS
     슈
    0.55
     점점
    0.52
     Kiến
    0.50
     საკ
    0.50
     불러
    0.49
     મહિના
    0.49
     ನಮ್ಮ
    0.49
    ಸೂ
    0.49
     Nearest
    0.49
    newParameter
    0.48
    Activations Density 0.001%

    No Known Activations