© 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. 5872
    Prev
    Next
    INDEX
    Explanations

    3

    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
     in
    0.86
    1
    0.80
     on
    0.80
    0
    0.71
     be
    0.66
    5
    0.64
     by
    0.63
    AN
    0.60
    9
    0.59
     to
    0.59
    POSITIVE LOGITS
    ﻤ
    0.73
     imasmim
    0.62
    나
    0.62
     desempen
    0.59
     adhipp
    0.59
     enfermed
    0.58
     poursuivre
    0.58
     compds
    0.58
     stades
    0.58
    ре
    0.57
    Activations Density 0.211%

    No Known Activations