© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221383
    Prev
    Next
    INDEX
    Explanations

    linking words and numbers

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

    dim sum

    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
    I
    0.54
    varepsilon
    0.49
    sc
    0.49
    A
    0.48
    mersive
    0.45
    乔
    0.45
    perp
    0.45
    DEFAULT
    0.44
     =)
    0.44
    hd
    0.43
    POSITIVE LOGITS
     suka
    0.50
    อนไลน์
    0.46
     graag
    0.46
     بیټینګ
    0.45
     hogi
    0.45
     mensual
    0.44
    டுகின்றன
    0.44
     mensal
    0.43
     structural
    0.42
    恽
    0.42
    Activations Density 0.001%

    No Known Activations