© 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. 222041
    Prev
    Next
    INDEX
    Explanations

    Dissertation Committee

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

    reports and recommendations

    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
     সমস্যা
    0.51
    畤
    0.50
    葷
    0.49
     क्रिप्टोकरेंसी
    0.48
    埆
    0.48
    ldre
    0.48
     paréntesis
    0.48
     問
    0.47
     電話
    0.46
     模型
    0.46
    POSITIVE LOGITS
    িতেছে
    0.48
    T
    0.47
    Pl
    0.47
     nitrate
    0.43
     It
    0.43
     Sta
    0.43
     string
    0.42
    S
    0.42
    A
    0.42
    Est
    0.42
    Activations Density 0.000%

    No Known Activations