© 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. 248299
    Prev
    Next
    INDEX
    Explanations

    tried earlier

    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
     النسبيه
    0.53
    墓志
    0.48
    淼
    0.46
    }}^{*}\
    0.46
    gels
    0.46
     方
    0.45
    졔
    0.45
    órm
    0.45
    '`--'`--
    0.45
    膛
    0.44
    POSITIVE LOGITS
     AND
    0.61
    il
    0.53
     NV
    0.53
     family
    0.51
     ise
    0.50
     same
    0.49
     Australian
    0.49
     ownership
    0.49
     tudi
    0.48
     foreground
    0.48
    Activations Density 0.001%

    No Known Activations