© 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. 177589
    Prev
    Next
    INDEX
    Explanations

    best selections best libraries actually

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

    face, assets, Clock, server, available

    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
     밝
    0.46
     ژوند
    0.44
     veditabbo
    0.44
     tomon
    0.44
    병
    0.43
    اہد
    0.42
     göst
    0.41
     proz
    0.41
    学历
    0.40
     현
    0.40
    POSITIVE LOGITS
    Stuart
    0.43
    其实
    0.42
    ੂ
    0.42
    playlist
    0.41
    visually
    0.40
    其實
    0.40
     vyroben
    0.40
    EventHandler
    0.40
    Sett
    0.39
    Fle
    0.39
    Activations Density 0.007%

    No Known Activations