© 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. 86157
    Prev
    Next
    INDEX
    Explanations

    words after specific punctuation

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

    **Core** Mechanics, **Kernel** Loading, **Everything**

    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
     activar
    0.51
     enzim
    0.50
    𝘺
    0.50
     ریس
    0.48
     ump
    0.48
     رمی
    0.47
     urea
    0.47
    ޔ
    0.47
     शर
    0.46
     chaplain
    0.46
    POSITIVE LOGITS
    据悉
    0.52
    分之一
    0.51
    mleri
    0.47
    fant
    0.47
    faction
    0.44
    firstname
    0.44
    Residential
    0.44
    agram
    0.43
    中
    0.43
    par
    0.43
    Activations Density 0.000%

    No Known Activations