© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 199157
    Prev
    Next
    INDEX
    Explanations

    connection, not outcome

    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
    ua
    0.46
    ienst
    0.45
    ные
    0.43
     gaze
    0.43
     sympath
    0.42
     antiseptic
    0.41
    珪
    0.41
    ucher
    0.41
    âh
    0.41
    雍
    0.40
    POSITIVE LOGITS
    overlapping
    0.40
     shoving
    0.40
     створення
    0.39
     indu
    0.39
     কারা
    0.38
     ľudí
    0.38
    ликт
    0.37
    外し
    0.36
     খেয়ে
    0.36
     malnutrition
    0.36
    Activations Density 0.005%

    No Known Activations