© 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-262K
    7. 205450
    Prev
    Next
    INDEX
    Explanations

    instructions involving containers or quantities

    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
    spannung
    0.48
    Automatic
    0.48
    symbol
    0.47
    ues
    0.47
    automatic
    0.47
    oping
    0.46
     အ
    0.45
    owska
    0.45
    ulations
    0.44
     automatic
    0.44
    POSITIVE LOGITS
    Ꮫ
    0.52
    ר
    0.52
     Blaine
    0.45
    м
    0.43
    ين
    0.43
    ي
    0.42
    ո
    0.42
    疲
    0.41
    敺
    0.41
    iniai
    0.39
    Activations Density 0.003%

    No Known Activations