© 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. 44127
    Prev
    Next
    INDEX
    Explanations

    Throughout fans

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

    wave displacement

    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
     definisi
    0.56
     نظری
    0.55
     ریاست
    0.50
     COLOR
    0.47
     gerakan
    0.47
     sguardo
    0.47
     Knesset
    0.46
    藐
    0.44
     Dresden
    0.44
     vela
    0.44
    POSITIVE LOGITS
    Comic
    0.46
     длиной
    0.46
    tang
    0.46
    Automatically
    0.43
    ién
    0.43
    栤
    0.43
    ాయి
    0.42
    Actual
    0.42
    杮
    0.42
    rest
    0.41
    Activations Density 0.001%

    No Known Activations