© 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. 245699
    Prev
    Next
    INDEX
    Explanations

    produced is

    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
     ocho
    0.50
     noodles
    0.49
     Sard
    0.49
     apoy
    0.48
     integrate
    0.48
    ට
    0.48
     unconsciously
    0.47
     escult
    0.47
     pesquisas
    0.47
     Chongqing
    0.47
    POSITIVE LOGITS
     Denial
    0.46
     לאחר
    0.45
    移民
    0.45
     RIGHTS
    0.45
    惶
    0.43
    ן
    0.42
    プレミアム
    0.40
    ลล์
    0.40
     reprint
    0.39
     denial
    0.39
    Activations Density 0.000%

    No Known Activations