© 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. 251786
    Prev
    Next
    INDEX
    Explanations

    specializes in

    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
    叟
    0.54
    詰
    0.52
    憫
    0.50
    诘
    0.49
    nosť
    0.48
    áciu
    0.47
     esperado
    0.47
    籀
    0.47
    فين
    0.46
    嬸
    0.46
    POSITIVE LOGITS
     accomplishments
    0.58
    ’
    0.52
     여
    0.47
    odymium
    0.46
     rew
    0.45
     achievements
    0.45
    foreach
    0.45
     responsive
    0.44
    łach
    0.44
     accomplishing
    0.44
    Activations Density 0.000%

    No Known Activations