© 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. 110726
    Prev
    Next
    INDEX
    Explanations

    codes and 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
     ведет
    0.57
    蝮
    0.54
    纪
    0.53
    MORDOR
    0.49
     ataque
    0.48
     pizarra
    0.48
    getBlueTeam
    0.48
     cuánto
    0.47
    ऑन
    0.47
    notlocked
    0.47
    POSITIVE LOGITS
    ere
    0.46
     pervasive
    0.46
     held
    0.45
    ?
    0.44
     uniform
    0.44
    _
    0.43
    {
    0.43
     resisted
    0.41
    0.41
    n
    0.41
    Activations Density 0.000%

    No Known Activations