© 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. 40200
    Prev
    Next
    INDEX
    Explanations

    for the

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

    or and can

    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
    ctus
    0.47
    리를
    0.46
     pathogenesis
    0.45
    ︾
    0.45
     Ι
    0.45
     알
    0.45
     Bison
    0.44
    리는
    0.44
    先に
    0.44
     Ethanol
    0.44
    POSITIVE LOGITS
    oq
    0.52
     Giveen
    0.48
    si
    0.46
    On
    0.45
     كده
    0.42
    tem
    0.42
    இது
    0.42
    voer
    0.42
    pyrid
    0.41
    }$
    0.41
    Activations Density 0.000%

    No Known Activations