© 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. 208897
    Prev
    Next
    INDEX
    Explanations

    birthday parties

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

    digital planners, wormholes, rhythm, TV, revolutionary

    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
     Bewert
    0.53
    瑀
    0.51
     Jü
    0.50
     Bewertung
    0.49
    ificação
    0.47
    igem
    0.46
    摭
    0.46
    𖥔
    0.46
    瞽
    0.46
     Namun
    0.45
    POSITIVE LOGITS
     closest
    0.46
    '
    0.43
     definitely
    0.42
     attraction
    0.42
     handy
    0.42
    (
    0.41
     cheapest
    0.41
     子
    0.39
     panning
    0.39
     GI
    0.39
    Activations Density 0.001%

    No Known Activations