© 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. 34857
    Prev
    Next
    INDEX
    Explanations

    task completion

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

    definitively identified

    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
    u
    0.65
    g
    0.55
    ul
    0.55
    be
    0.54
    lar
    0.54
    ut
    0.53
    j
    0.53
    l
    0.52
    amat
    0.52
    ua
    0.52
    POSITIVE LOGITS
     douche
    0.52
     pollute
    0.52
     outils
    0.50
     tâches
    0.50
     fournis
    0.50
     zwięks
    0.50
     oppress
    0.48
    сіі
    0.48
     stockpile
    0.47
    任務
    0.47
    Activations Density 0.000%

    No Known Activations