© 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. 37723
    Prev
    Next
    INDEX
    Explanations

    official statements or descriptions

    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
     dreaded
    0.43
    強制
    0.42
     acidic
    0.41
     thought
    0.40
     tendency
    0.39
     forcing
    0.38
    pathy
    0.38
    後
    0.37
     acidified
    0.37
    )}$.
    0.36
    POSITIVE LOGITS
     descripción
    0.80
     description
    0.77
     describes
    0.69
    Description
    0.68
    官方
    0.67
     descrição
    0.67
     Description
    0.66
     tout
    0.66
     descrizione
    0.66
    描述
    0.65
    Activations Density 0.082%

    No Known Activations