© 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. 219219
    Prev
    Next
    INDEX
    Explanations

    moving day

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

    pre-defined purposes and frameworks

    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
     因为
    0.52
     叶
    0.52
     действу
    0.49
     类
    0.48
     изначально
    0.48
     马
    0.47
     Tara
    0.47
     период
    0.47
    依旧
    0.47
     मिल्क
    0.46
    POSITIVE LOGITS
     treaties
    0.46
    $',
    0.46
    hes
    0.44
    Ts
    0.44
     despatch
    0.44
    ťaž
    0.43
    atis
    0.41
    רת
    0.41
    ricing
    0.41
    rocities
    0.41
    Activations Density 0.001%

    No Known Activations