© 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. 238169
    Prev
    Next
    INDEX
    Explanations

    live for righteousness

    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
     غال
    0.52
    textrm
    0.49
     ҳ
    0.45
    <unused16>
    0.45
    ым
    0.45
    排放
    0.44
     रॉ
    0.44
     बातम्या
    0.44
    ेंसेस
    0.43
    Synced
    0.43
    POSITIVE LOGITS
    i
    0.55
    \
    0.52
    owanie
    0.51
     인한
    0.50
    지
    0.50
     okra
    0.49
    sh
    0.48
     あり
    0.48
    de
    0.48
     Aarti
    0.47
    Activations Density 0.000%

    No Known Activations