© 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. 163268
    Prev
    Next
    INDEX
    Explanations

    restrictions and projects

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

    restrictions and prohibitions

    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
     tám
    0.50
     krvi
    0.50
     legjobb
    0.47
     يجب
    0.47
    輕
    0.45
    應
    0.45
    ře
    0.45
     peč
    0.44
    </tr>
    0.43
     musí
    0.43
    POSITIVE LOGITS
     certifications
    0.52
    کلی
    0.49
     periods
    0.49
     subtypes
    0.47
     protocols
    0.47
     Refs
    0.47
     தடை
    0.47
     prohibits
    0.46
     prohibitions
    0.46
     لیتے
    0.46
    Activations Density 0.000%

    No Known Activations