© 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. 46567
    Prev
    Next
    INDEX
    Explanations

    Firstly, crumble, scales, positive

    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
    ور
    0.52
    ف
    0.46
    र
    0.44
    لس
    0.43
    Mitsubishi
    0.42
    را
    0.42
    此之外
    0.42
    Segment
    0.41
    ர
    0.41
    간
    0.41
    POSITIVE LOGITS
     داد
    0.48
     nez
    0.47
    ärg
    0.47
     Cheer
    0.47
     ker
    0.46
     হাড়
    0.45
     cheer
    0.44
    icznych
    0.44
     తే
    0.43
     huid
    0.43
    Activations Density 0.000%

    No Known Activations