© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5335
    Prev
    Next
    INDEX
    Explanations

    identifying or clarifying statements

    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
    ↵
    0.38
    و
    0.35
    ορ
    0.31
    RIA
    0.31
    探
    0.31
    도
    0.30
    給
    0.30
    лее
    0.30
    دي
    0.30
    且
    0.29
    POSITIVE LOGITS
     this
    0.52
     it
    0.49
     these
    0.48
     ഇത്
    0.47
     This
    0.46
     thefe
    0.44
     They
    0.43
     These
    0.43
     It
    0.42
     هذا
    0.41
    Activations Density 0.041%

    No Known Activations