© 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. 23482
    Prev
    Next
    INDEX
    Explanations

    lists headlines and availability

    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
     compañ
    0.54
     contamin
    0.52
     situações
    0.52
    ﻙ
    0.50
    kbar
    0.49
     tincidunt
    0.48
     experimentos
    0.48
     nörd
    0.48
    gages
    0.47
     determin
    0.46
    POSITIVE LOGITS
    用
    0.51
    мо
    0.43
    По
    0.42
    М
    0.42
    格
    0.42
    車
    0.42
     Driver
    0.42
    提
    0.42
    면
    0.42
    ovich
    0.41
    Activations Density 0.001%

    No Known Activations