© 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. 138086
    Prev
    Next
    INDEX
    Explanations

    legally permissible degree university

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

    AT, IL, EE, TV, or Address

    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
    〇
    0.47
    ﮕ
    0.47
     chiesa
    0.46
     texted
    0.46
     Casa
    0.45
     văn
    0.45
    恰
    0.44
    ぴったり
    0.44
     பொரு
    0.43
    տ
    0.43
    POSITIVE LOGITS
    و
    0.47
    خ
    0.45
     captives
    0.44
    യ്യാ
    0.42
    íny
    0.42
    idase
    0.41
    เพ
    0.40
    వీ
    0.40
     לק
    0.40
    ول
    0.39
    Activations Density 0.000%

    No Known Activations