© 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. 173464
    Prev
    Next
    INDEX
    Explanations

    Connecticut Arts

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

    standard, permissions, or workspace

    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
    امر
    0.47
    潛
    0.46
    культур
    0.43
    ทั้ง
    0.43
    蕭
    0.43
    канчи
    0.42
     descends
    0.42
    老闆
    0.42
    雙
    0.42
    狂
    0.41
    POSITIVE LOGITS
    xm
    0.49
     পাচ
    0.48
    reci
    0.45
     jugador
    0.45
     gimnas
    0.45
     XM
    0.45
     Neurol
    0.44
     पाँच
    0.44
    fulfilled
    0.44
     सेवक
    0.42
    Activations Density 0.002%

    No Known Activations