© 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. 51391
    Prev
    Next
    INDEX
    Explanations

    PDFs and caches

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

    rootkits, selection, carry genes

    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
    مبر
    0.52
     guérir
    0.50
     bernama
    0.47
    னிய
    0.47
    రు
    0.46
    吼
    0.46
     solucionar
    0.46
    庣
    0.46
    ινων
    0.46
    мести
    0.46
    POSITIVE LOGITS
    in
    0.58
    le
    0.58
    cache
    0.55
     in
    0.54
    ev
    0.54
    ag
    0.54
    folders
    0.54
     caches
    0.54
     PDFs
    0.53
    e
    0.52
    Activations Density 0.000%

    No Known Activations