© 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. 239382
    Prev
    Next
    INDEX
    Explanations

    certifications and termination

    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
    ouer
    0.54
     ഞാൻ
    0.52
    聃
    0.46
    読む
    0.45
     दाम
    0.42
    verbal
    0.42
     그렇게
    0.41
     verbal
    0.41
     overtaking
    0.41
     કરશે
    0.40
    POSITIVE LOGITS
     aplica
    0.45
     Fortsch
    0.45
    smöglichkeiten
    0.45
    ಸಿ
    0.45
     Demon
    0.44
     Administração
    0.43
    失效
    0.42
    Í
    0.42
     طی
    0.42
    لی
    0.41
    Activations Density 0.000%

    No Known Activations