© 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. 183587
    Prev
    Next
    INDEX
    Explanations

    King Charles, shape similar, County offers

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

    being constantly, not just, when proper

    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
    fixing
    0.49
    ↯
    0.49
    rollback
    0.48
     নির্
    0.47
    industrial
    0.47
     eki
    0.47
    FRING
    0.47
    انیه
    0.46
     liquidated
    0.46
    НИ
    0.45
    POSITIVE LOGITS
    حب
    0.46
    നെ
    0.45
    柟
    0.44
     Wed
    0.42
     campagnes
    0.41
    Datab
    0.40
    我们在
    0.40
     interiores
    0.40
     DBHelper
    0.40
    Wed
    0.39
    Activations Density 0.000%

    No Known Activations