© 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. 104423
    Prev
    Next
    INDEX
    Explanations

    ahead of invention

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

    finding vulnerabilities in code

    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
    닛
    0.52
     codice
    0.50
    ર્મા
    0.50
    ண்ட
    0.49
     stile
    0.48
     romanzo
    0.48
    functie
    0.47
     atenção
    0.46
    州
    0.46
    咎
    0.46
    POSITIVE LOGITS
     (
    0.59
     ls
    0.50
    .
    0.50
    ta
    0.48
     %
    0.48
     Stages
    0.47
    ampions
    0.46
     ratione
    0.46
    uc
    0.46
    Enc
    0.45
    Activations Density 0.000%

    No Known Activations