© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47627
    Prev
    Next
    INDEX
    Explanations

    specialized technical context

    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
     Office
    0.53
    гу
    0.47
     Provider
    0.46
    ,+\
    0.46
    hauses
    0.45
     näytt
    0.45
     =>
    0.44
    ⟹
    0.44
     Protection
    0.44
    Equivalent
    0.43
    POSITIVE LOGITS
     theology
    0.46
    enburg
    0.46
     disputa
    0.45
    ﻭ
    0.45
    encode
    0.44
     ছিন
    0.44
     ﺍﻟ
    0.43
     druga
    0.43
     که
    0.43
     encode
    0.42
    Activations Density 0.000%

    No Known Activations