© 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. 149535
    Prev
    Next
    INDEX
    Explanations

    honor, protection, need

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

    demonic possession, understanding the

    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
    h
    0.48
    kräfte
    0.48
    ungk
    0.47
    req
    0.45
    algorithms
    0.45
    k
    0.45
    w
    0.44
    ut
    0.43
    raq
    0.43
    nd
    0.43
    POSITIVE LOGITS
    ტო
    0.52
    وني
    0.48
    <>();
    0.47
     cruising
    0.46
    碚
    0.46
    фикации
    0.46
     landing
    0.45
    يير
    0.45
    していました
    0.45
    بعاد
    0.45
    Activations Density 0.000%

    No Known Activations