© 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-16K
    7. 7881
    Prev
    Next
    INDEX
    Explanations

    user input for parameters and commands

    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_16k_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
    та
    0.96
    ，
    0.82
    마
    0.79
     UBND
    0.78
     が
    0.77
    的关系
    0.75
     testacé
    0.73
     수
    0.73
    の前
    0.73
    的最
    0.72
    POSITIVE LOGITS
    ig
    1.29
    i
    1.22
    ib
    1.16
    et
    1.13
    d
    1.01
    or
    0.98
    n
    0.93
    ou
    0.92
    es
    0.90
    ic
    0.90
    Activations Density 0.063%

    No Known Activations