© 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. 89852
    Prev
    Next
    INDEX
    Explanations

    old, kami, pun, based on, certain extent

    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
    KCl
    0.47
    (",");
    0.47
    EventManager
    0.47
     elektri
    0.46
    agm
    0.45
     Adverse
    0.45
    Gregor
    0.45
    Dade
    0.44
    Champ
    0.44
     restoran
    0.44
    POSITIVE LOGITS
    ியும்
    0.52
    𝙮
    0.49
     खासा
    0.46
    रहे
    0.46
    ರ್
    0.44
    𝙞
    0.44
    សូម
    0.43
    頗
    0.43
     ਵੀ
    0.43
    াউন
    0.42
    Activations Density 0.001%

    No Known Activations