© 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. 72403
    Prev
    Next
    INDEX
    Explanations

    history and use

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

    examples, GPUs, 5 year parts

    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
     금액
    0.48
     Разби
    0.46
     whatever
    0.45
     VIDEO
    0.45
    eniendo
    0.45
     ItemStack
    0.44
     {}",
    0.44
     動画
    0.44
    phalodes
    0.44
     Количество
    0.43
    POSITIVE LOGITS
    listdir
    0.45
    Lic
    0.45
     utilization
    0.43
    otar
    0.41
    renewal
    0.41
     propositions
    0.41
     prayers
    0.40
    ویز
    0.40
     slices
    0.40
     passare
    0.40
    Activations Density 0.002%

    No Known Activations