© 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-262K
    7. 168678
    Prev
    Next
    INDEX
    Explanations

    However, visual record

    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
    แส
    0.49
    assign
    0.43
    диви
    0.42
    Matrices
    0.41
    Allocate
    0.41
    Blocked
    0.41
    T
    0.40
    Inf
    0.39
    ॅ
    0.39
    Hayes
    0.38
    POSITIVE LOGITS
     Germany
    0.48
     influencia
    0.44
     मुहिम
    0.44
     전달
    0.44
     Technically
    0.44
     ہل
    0.43
     Jerman
    0.43
     unterstüt
    0.42
     공간
    0.42
     an
    0.41
    Activations Density 0.014%

    No Known Activations