© 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. 228468
    Prev
    Next
    INDEX
    Explanations

    broken objects and conditions

    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
    amia
    0.52
    必备
    0.52
    álogo
    0.50
    ire
    0.47
    🔝
    0.45
    ());
    0.44
    ieuse
    0.44
    á
    0.44
    uce
    0.42
    ewomen
    0.42
    POSITIVE LOGITS
    िन
    0.51
     kotak
    0.48
     espace
    0.48
    КС
    0.47
     primordial
    0.47
    AKES
    0.47
     numerosos
    0.46
     unterschiedlich
    0.46
    新型コロナ
    0.46
    सम
    0.45
    Activations Density 0.000%

    No Known Activations