© 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-65K
    7. 48144
    Prev
    Next
    INDEX
    Explanations

    game titles, proper nouns

    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_65k_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
     ἢ
    0.45
     TED
    0.44
     unwillingness
    0.43
     reluctance
    0.42
    lective
    0.42
     نريد
    0.41
    otives
    0.41
    Thay
    0.41
     تغيير
    0.40
     Whose
    0.40
    POSITIVE LOGITS
    も
    0.46
     hón
    0.44
    ेंद्र
    0.44
    도
    0.43
    があります
    0.42
    тата
    0.42
    鸥
    0.41
     보인다
    0.40
     parr
    0.39
    감
    0.39
    Activations Density 0.003%

    No Known Activations