© 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. 70652
    Prev
    Next
    INDEX
    Explanations

    organization and subject matter

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

    providing justifications and descriptions

    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
     หนึ่ง
    0.48
     wysokości
    0.47
     ℝ
    0.47
     ≤
    0.47
    ❁
    0.46
     invierno
    0.46
    ബരിമല
    0.46
     bisschen
    0.45
     немного
    0.45
     წ
    0.45
    POSITIVE LOGITS
     Mannes
    0.54
    由於
    0.48
     Psychological
    0.44
     These
    0.40
    માંથી
    0.39
     Psychology
    0.39
    ORGAN
    0.39
    AddTask
    0.38
     functioning
    0.38
     SIR
    0.38
    Activations Density 0.000%

    No Known Activations