© 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. 92497
    Prev
    Next
    INDEX
    Explanations

    concepts and criteria for change

    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
     ingin
    0.48
    ې
    0.46
    ود
    0.46
     enig
    0.46
    ند
    0.46
     sometimes
    0.45
     iš
    0.44
     evoc
    0.43
     oma
    0.42
     duen
    0.42
    POSITIVE LOGITS
    Type
    0.45
    atien
    0.45
    腚
    0.42
    শিক্ষা
    0.42
     স্রো
    0.42
    getDouble
    0.42
    лната
    0.42
    iffer
    0.42
    ilin
    0.42
    ,$$
    0.42
    Activations Density 0.009%

    No Known Activations