© 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. 132381
    Prev
    Next
    INDEX
    Explanations

    man raised

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

    overall summaries and general conditions

    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
    ir
    0.57
    si
    0.53
    。
    0.49
    чает
    0.47
    che
    0.47
    son
    0.46
    s
    0.46
    is
    0.46
     tiller
    0.46
    чка
    0.45
    POSITIVE LOGITS
     llevaba
    0.49
    㑅
    0.48
     پیسو
    0.46
    થી
    0.46
     Kxa
    0.45
     باسک
    0.45
    করি
    0.45
    भंगा
    0.45
     பணியா
    0.44
     personnelle
    0.44
    Activations Density 0.001%

    No Known Activations