© 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. 35222
    Prev
    Next
    INDEX
    Explanations

    building or synthesizing information

    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
    学位
    0.46
    年以上
    0.45
    *\
    0.45
    紹介
    0.44
    一
    0.44
    竣工
    0.44
    する
    0.42
    開催
    0.42
    htb
    0.42
    й
    0.42
    POSITIVE LOGITS
     certeza
    0.51
    يل
    0.49
     mantém
    0.49
     சிவப்பு
    0.49
     alguien
    0.48
    CLUSTERED
    0.48
     bulge
    0.47
     istek
    0.47
     ني
    0.47
     प्रतिनिध
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.