© 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. 101133
    Prev
    Next
    INDEX
    Explanations

    surprisingly enough

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

    named, VirtualAlloc, ring tattoos

    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
    Protein
    0.52
    נ
    0.51
    茆
    0.51
     mat
    0.50
     Pharmacology
    0.48
    おい
    0.48
    ยา
    0.47
    SubDirectory
    0.47
     spettacolo
    0.47
    涕
    0.46
    POSITIVE LOGITS
    name
    0.46
    nings
    0.46
    vis
    0.46
    ning
    0.45
     meandering
    0.44
    args
    0.44
    market
    0.43
     воск
    0.43
     प्रखंड
    0.42
    vals
    0.42
    Activations Density 0.001%

    No Known Activations