© 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. 40420
    Prev
    Next
    INDEX
    Explanations

    social intelligence, learning, kin recognition

    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
     기대
    0.49
    使用
    0.44
     ఫ
    0.41
    expected
    0.41
    у
    0.40
    vscode
    0.40
    ugo
    0.40
    すれば
    0.39
    incredible
    0.39
    ﾌ
    0.39
    POSITIVE LOGITS
    δυ
    0.46
    PAF
    0.44
     topography
    0.42
     paddingTop
    0.42
     نیست
    0.42
     biennial
    0.40
     Estonian
    0.40
     primordial
    0.40
     مشغول
    0.39
    τούν
    0.39
    Activations Density 0.003%

    No Known Activations