© 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. 245056
    Prev
    Next
    INDEX
    Explanations

    search for

    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
    C
    0.58
    י
    0.55
    i
    0.55
    D
    0.54
    U
    0.52
    Applied
    0.49
    袖
    0.47
    S
    0.47
    Wil
    0.47
    Soil
    0.46
    POSITIVE LOGITS
    assaytype
    0.48
     évol
    0.47
    iguë
    0.47
     pTM
    0.47
     poisson
    0.45
     aventure
    0.45
    parsedBlock
    0.45
     cristall
    0.44
    smouth
    0.44
     குற்றம்
    0.44
    Activations Density 0.000%

    No Known Activations