© 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-262K
    7. 54923
    Prev
    Next
    INDEX
    Explanations

    engine, building

    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
     konkret
    0.48
    㭉
    0.48
     gebe
    0.45
    லக
    0.45
    డే
    0.45
    ემი
    0.44
     successor
    0.43
     remix
    0.43
     kultur
    0.42
    أة
    0.42
    POSITIVE LOGITS
    𝗼
    0.51
     أنّ
    0.49
    ort
    0.46
    lu
    0.46
    𝐧
    0.46
    lar
    0.44
    lara
    0.44
    𝗮
    0.44
    quo
    0.43
     புரி
    0.42
    Activations Density 0.002%

    No Known Activations