© 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. 122335
    Prev
    Next
    INDEX
    Explanations

    notwithstanding Directive

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

    git fetch, command output, communicate

    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
    ell
    0.52
    ↵
    0.52
    Sci
    0.50
    ci
    0.50
    ian
    0.50
    T
    0.50
     coordinator
    0.49
     RAY
    0.48
     ed
    0.48
     organ
    0.48
    POSITIVE LOGITS
     عطا
    0.45
    ဋ
    0.44
    ajos
    0.43
    дания
    0.43
    Appending
    0.43
    ی
    0.42
     обстоя
    0.42
     놓고
    0.42
     spoilt
    0.42
    िशियल
    0.42
    Activations Density 0.001%

    No Known Activations