© 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. 32753
    Prev
    Next
    INDEX
    Explanations

    of public, a doctrine

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

    tracking standards

    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
    Valor
    0.46
     שנ
    0.45
    לה
    0.43
    莪
    0.42
     சிற
    0.41
    soaked
    0.41
    䔬
    0.41
    ورش
    0.41
    ೯
    0.40
    テム
    0.40
    POSITIVE LOGITS
     physician
    0.45
     Medicare
    0.45
     Gautam
    0.45
     Foreign
    0.44
     presumably
    0.44
     medicare
    0.44
     Afghanistan
    0.43
     Russia
    0.43
     Timatic
    0.43
    ですね
    0.43
    Activations Density 0.000%

    No Known Activations