© 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. 153781
    Prev
    Next
    INDEX
    Explanations

    classified alcohol economy acquired cheese

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

    common csv file import

    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
     मेटल
    0.55
    för
    0.52
    uidade
    0.52
    ulo
    0.50
    urnama
    0.48
    %。
    0.48
     約
    0.46
    utada
    0.46
    uncia
    0.46
    
    0.46
    POSITIVE LOGITS
     spontaneous
    0.54
     everything
    0.50
     blame
    0.45
    RICAL
    0.45
     disabling
    0.44
     possible
    0.44
     anabolic
    0.44
     cyclic
    0.44
    යා
    0.44
     myosin
    0.44
    Activations Density 0.000%

    No Known Activations