© 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. 239278
    Prev
    Next
    INDEX
    Explanations

    quality care and support

    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
    時
    0.55
    他們的
    0.52
     त्यांची
    0.52
    హి
    0.50
    組合
    0.49
     பாபிலோ
    0.49
    вото
    0.48
    Сто
    0.47
    X
    0.47
     അവരുടെ
    0.47
    POSITIVE LOGITS
     wrestling
    0.44
     dynamite
    0.44
     đẹp
    0.43
     dampers
    0.43
    ajjati
    0.42
     diathermy
    0.42
     exerts
    0.41
     bądź
    0.41
     tackling
    0.40
     wasps
    0.40
    Activations Density 0.001%

    No Known Activations