© 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. 42123
    Prev
    Next
    INDEX
    Explanations

    biological studies

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

    sent in writing

    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
    मिया
    0.54
    耶稣
    0.54
    舂
    0.54
    াশ
    0.52
     प्रेरणात्मक
    0.51
    娜
    0.50
    MathMarks
    0.49
    新闻
    0.49
     شمال
    0.49
    曛
    0.48
    POSITIVE LOGITS
     cells
    0.57
     ligands
    0.54
     baryons
    0.54
     interacts
    0.52
     binds
    0.51
     satisfies
    0.51
     shields
    0.51
     stores
    0.50
     tokamaks
    0.50
     ston
    0.49
    Activations Density 0.000%

    No Known Activations