© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179007
    Prev
    Next
    INDEX
    Explanations

    distinguishing specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    technical procedures and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     совер
    0.52
    नी
    0.50
    找到
    0.50
    步
    0.49
    μα
    0.49
    す
    0.48
    沃尔
    0.47
    พ
    0.46
    ى
    0.46
    日
    0.46
    POSITIVE LOGITS
    olí
    0.51
    ಿಲ್ಲ
    0.46
     এরই
    0.46
     lathe
    0.44
     complémentaires
    0.43
    eper
    0.42
    zerw
    0.41
    Escolhido
    0.41
     کھولنے
    0.41
     candidature
    0.41
    Activations Density 0.002%

    No Known Activations