© 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. 122831
    Prev
    Next
    INDEX
    Explanations

    triggered Threshold

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

    dwarves

    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
     ஒவ்வொரு
    0.45
    แต่ละ
    0.45
     each
    0.43
    ᴇ
    0.42
    くり
    0.42
    each
    0.42
    ilver
    0.42
    sorry
    0.41
     nell
    0.40
     ใน
    0.39
    POSITIVE LOGITS
     hiszen
    0.46
     Đế
    0.43
     说明
    0.42
     সেটা
    0.42
    <>(
    0.42
     responsáveis
    0.42
     gdyż
    0.41
     fác
    0.41
     querida
    0.41
     श्रद्धाल
    0.41
    Activations Density 0.000%

    No Known Activations