© 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. 216491
    Prev
    Next
    INDEX
    Explanations

    frauen, cek, bardzo, extrêmement

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

    record-keepers, two, remaining

    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
    шко
    0.50
    SwitchCompat
    0.48
    亾
    0.46
    ن
    0.44
    ਕ
    0.44
    亼
    0.44
    Lifestyle
    0.43
    Տ
    0.43
    زور
    0.43
    στε
    0.43
    POSITIVE LOGITS
     feeble
    0.50
     frauen
    0.49
     reverber
    0.46
     cek
    0.46
     wore
    0.46
     bombing
    0.45
     up
    0.45
     bardzo
    0.45
     extrêmement
    0.45
     furthering
    0.45
    Activations Density 0.001%

    No Known Activations