© 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. 37416
    Prev
    Next
    INDEX
    Explanations

    business and outcomes

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

    executable file format

    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
    Identifier
    0.47
    edTest
    0.47
    ]</
    0.46
     елект
    0.45
     হাতে
    0.43
    uckland
    0.41
    骼
    0.41
     кле
    0.40
     발행
    0.39
    }]{
    0.39
    POSITIVE LOGITS
     cultiv
    0.59
     universo
    0.54
    dert
    0.54
     Continuity
    0.52
     continuidad
    0.52
     sabi
    0.50
     verme
    0.50
     resurrect
    0.49
     gesto
    0.49
     devs
    0.49
    Activations Density 0.000%

    No Known Activations