© 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. 194336
    Prev
    Next
    INDEX
    Explanations

    hanging leg, calendar template

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

    red sauce

    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
    स्तक
    0.56
     gwiaz
    0.53
    aktual
    0.52
    泂
    0.52
    ự
    0.51
    ્યો
    0.51
    憧
    0.50
    нець
    0.50
     commemorate
    0.47
     descubre
    0.47
    POSITIVE LOGITS
    u
    0.54
    Simplified
    0.45
    Trusted
    0.45
     Warnings
    0.45
     guts
    0.43
     değ
    0.42
     முடிந்த
    0.41
    dings
    0.41
     ns
    0.41
    trecht
    0.41
    Activations Density 0.000%

    No Known Activations