© 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. 112902
    Prev
    Next
    INDEX
    Explanations

    specific advice or details

    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
     prolifer
    0.52
    形で
    0.50
    Ꮹ
    0.50
    பிற
    0.49
     Authorization
    0.48
    猊
    0.47
    紆
    0.46
     Gora
    0.46
    厛
    0.46
     Albania
    0.46
    POSITIVE LOGITS
    c
    0.56
    ad
    0.47
    ulations
    0.46
    ge
    0.45
    achment
    0.45
    ILLE
    0.45
    ere
    0.44
    i
    0.44
    ille
    0.44
    atch
    0.43
    Activations Density 0.000%

    No Known Activations