© 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. 144311
    Prev
    Next
    INDEX
    Explanations

    confirmation, downloads, moments, Mill, Bartholomew

    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
    કમાં
    0.49
     misalignment
    0.46
    line
    0.42
    ୍କ
    0.41
    defeat
    0.41
    man
    0.41
    p
    0.40
    alignment
    0.40
    stop
    0.39
    switch
    0.39
    POSITIVE LOGITS
     letzten
    0.43
    섣
    0.43
     سرب
    0.42
     অম
    0.41
     flav
    0.41
     ribosomal
    0.41
     من
    0.40
     noved
    0.40
     شاعر
    0.39
     snowy
    0.39
    Activations Density 0.009%

    No Known Activations