© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30417
    Prev
    Next
    INDEX
    Explanations

    embeddings, year, ink

    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_65k_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
     ٹوٹ
    0.49
     zigzag
    0.43
    irittura
    0.43
    뭅
    0.43
    ಬ್ಬಿಣ
    0.43
    udahkan
    0.43
    ㅀ
    0.43
    𝚄
    0.43
    เลต
    0.42
    proguard
    0.42
    POSITIVE LOGITS
     ,
    0.57
    ,
    0.55
     based
    0.52
     depending
    0.50
    J
    0.50
    +,
    0.47
    ,,
    0.47
    ',
    0.47
    te
    0.46
     initially
    0.46
    Activations Density 0.000%

    No Known Activations