© 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. 247385
    Prev
    Next
    INDEX
    Explanations

    off phrase continuations

    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
    typedef
    0.44
     지
    0.43
     질
    0.43
    型の
    0.43
    ‰
    0.42
     Tian
    0.42
    เวลา
    0.42
    この
    0.41
     MRD
    0.41
     vitam
    0.41
    POSITIVE LOGITS
     wobec
    0.43
    నె
    0.41
    ಗ
    0.41
     राजपूत
    0.41
    伱
    0.40
    টর
    0.40
     inférieurs
    0.40
     الجنوب
    0.39
     contribuir
    0.39
    ('.')
    0.39
    Activations Density 0.001%

    No Known Activations