© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12169
    Prev
    Next
    INDEX
    Explanations

    codes or identifiers

    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
    बिलिटी
    0.27
     tumorigen
    0.26
     gacche
    0.25
     renversement
    0.25
    疳
    0.25
     sanguí
    0.25
    ἵ
    0.25
    胙
    0.25
    ynaptic
    0.25
     экскур
    0.24
    POSITIVE LOGITS
    0
    0.36
    /
    0.34
    1
    0.33
    +
    0.33
    5
    0.29
    -
    0.28
    3
    0.28
    4
    0.28
    7
    0.28
    well
    0.27
    Activations Density 0.218%

    No Known Activations