© 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. 217185
    Prev
    Next
    INDEX
    Explanations

    pm ,

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

    discussing or listing items

    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
    用於
    0.44
     واقع
    0.44
     блоки
    0.43
     matches
    0.42
    ayers
    0.41
     internals
    0.40
    飭
    0.40
     зачем
    0.39
    隂
    0.39
     لأ
    0.39
    POSITIVE LOGITS
     intricate
    0.49
     curled
    0.47
    antz
    0.47
    ligi
    0.47
    ipeline
    0.46
    ുകൂ
    0.45
    lidir
    0.45
    gı
    0.44
     pista
    0.44
    ksz
    0.44
    Activations Density 0.000%

    No Known Activations