© 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. 52352
    Prev
    Next
    INDEX
    Explanations

    code or conversational continuations

    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
     concaten
    0.41
    ('''
    0.41
     във
    0.41
    У
    0.41
    ésre
    0.39
    aih
    0.39
    抔
    0.39
    str
    0.38
     लोका
    0.38
    ough
    0.38
    POSITIVE LOGITS
    "
    0.41
    Responding
    0.40
    ленной
    0.36
     আনা
    0.36
    সী
    0.34
    Relations
    0.34
    GlobalSection
    0.34
     relat
    0.34
    ੀ
    0.34
     térm
    0.33
    Activations Density 0.001%

    No Known Activations