© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9271
    Prev
    Next
    INDEX
    Explanations

    thunder combinations

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

    apt upgrade, theme

    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_40_width_16k_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
     Equations
    0.41
    infodisc
    0.39
    linalg
    0.39
     Brend
    0.39
    ))&&(
    0.39
     pthread
    0.39
     lớn
    0.38
     Matth
    0.38
     সিদ্ধান্তে
    0.38
    чними
    0.37
    POSITIVE LOGITS
    Marker
    0.46
    marker
    0.40
    টারি
    0.40
    🚛
    0.39
    は見
    0.39
    淘
    0.38
    BJ
    0.38
    upiter
    0.38
    ム
    0.38
    PAP
    0.37
    Activations Density 0.014%

    No Known Activations