© 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. 11802
    Prev
    Next
    INDEX
    Explanations

    technical coursework

    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
     சரியான
    0.44
    ни
    0.43
     предо
    0.42
    }
    0.42
     д
    0.42
     на
    0.41
     не
    0.41
     пусть
    0.41
    M
    0.41
     RESON
    0.40
    POSITIVE LOGITS
     pavilions
    0.47
    环境
    0.46
     ग्लास
    0.44
     ऑक्साइड
    0.43
     galleries
    0.43
     histidine
    0.42
     oxidation
    0.41
    ያን
    0.41
    电影
    0.40
    环境中
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.