© 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. 91273
    Prev
    Next
    INDEX
    Explanations

    Reuben Foster and automatic formatting

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

    code, diagram, and media types

    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
    晎
    0.54
    <unused584>
    0.52
    }}$.
    0.52
    ısının
    0.52
    
    0.48
    <unused983>
    0.48
     घरात
    0.47
    <unused1096>
    0.47
    <unused1881>
    0.47
    。”
    0.47
    POSITIVE LOGITS
    Trailer
    0.47
     besz
    0.46
     Trailer
    0.45
    So
    0.43
     temp
    0.43
     trailer
    0.42
    Asp
    0.41
     Герма
    0.41
    ल्ज
    0.41
     grounds
    0.41
    Activations Density 0.000%

    No Known Activations