© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92318
    Prev
    Next
    INDEX
    Explanations

    specifying quantities or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﻔ
    0.48
    VAE
    0.46
    ट
    0.46
    ูด
    0.46
     CARE
    0.44
    GRADE
    0.44
    uestro
    0.44
     гульнявыя
    0.44
    䐈
    0.42
     PRICE
    0.42
    POSITIVE LOGITS
     thisTrack
    0.48
    colLast
    0.48
     AppBsky
    0.48
    ißler
    0.46
    mActivity
    0.46
     учё
    0.46
     resetCounters
    0.46
    thisComponent
    0.46
    nBitCount
    0.46
     úč
    0.45
    Activations Density 0.003%

    No Known Activations