© 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. 95393
    Prev
    Next
    INDEX
    Explanations

    buy, Shop, or Store context

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

    configure AWS IAM

    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
     وبعد
    0.44
    ামী
    0.43
    ן
    0.43
     vertreten
    0.42
    getAll
    0.42
     hoofd
    0.42
     verste
    0.42
     Hagan
    0.42
     oversees
    0.42
    verts
    0.41
    POSITIVE LOGITS
     خفی
    0.47
     சக்த
    0.45
     आविष्कार
    0.44
     संख्याओं
    0.43
     transforma
    0.42
     Psychiatry
    0.41
     appendage
    0.41
    癡
    0.40
     carcinomas
    0.40
     vững
    0.39
    Activations Density 0.000%

    No Known Activations