© 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. 6830
    Prev
    Next
    INDEX
    Explanations

    level of detail comparison

    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
     Ech
    0.43
     θεω
    0.38
    utérus
    0.37
     ลักษณะ
    0.37
    ลักษณะ
    0.37
     Travers
    0.37
    '}).
    0.36
    ix
    0.36
    heiten
    0.36
    𝑃
    0.36
    POSITIVE LOGITS
     downright
    0.91
     outright
    0.85
     zelfs
    0.80
     addirittura
    0.77
    甚至
    0.76
     sogar
    0.75
     incluso
    0.73
     bahkan
    0.71
     thậm
    0.68
     even
    0.66
    Activations Density 0.153%

    No Known Activations