© 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. 7042
    Prev
    Next
    INDEX
    Explanations

    based on

    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
     usurp
    0.51
    ﻊ
    0.50
     такое
    0.49
     abuso
    0.48
     exaggerate
    0.48
     exagger
    0.47
     flamboyant
    0.47
     subterr
    0.47
     duż
    0.47
     cynical
    0.47
    POSITIVE LOGITS
    ס
    0.56
    ’
    0.55
    情况
    0.54
     on
    0.52
     whichever
    0.51
    criteria
    0.50
    с
    0.50
    公式
    0.48
     Based
    0.47
    its
    0.46
    Activations Density 0.173%

    No Known Activations