© 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. 203330
    Prev
    Next
    INDEX
    Explanations

    corporate profile

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

    Fluid Intelligence

    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
    gående
    0.49
     Fleurs
    0.46
    祿
    0.46
    buscador
    0.45
    <0xB2>
    0.45
     mismos
    0.44
     tumult
    0.44
     而且
    0.44
     Chirurgien
    0.43
    leurs
    0.43
    POSITIVE LOGITS
     recombinant
    0.52
    WZ
    0.47
    情报
    0.47
    ppm
    0.46
    impurity
    0.45
     mantém
    0.44
     کریم
    0.43
     اسلامی
    0.43
    ¯</
    0.43
     গণ্য
    0.42
    Activations Density 0.001%

    No Known Activations