© 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. 103817
    Prev
    Next
    INDEX
    Explanations

    crusher, grinding, screening, machine

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

    financial, Virtual, linux, en, pav

    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
     بیٹ
    0.52
     था
    0.50
     थी
    0.48
    glise
    0.47
    ido
    0.45
    avno
    0.45
    \`
    0.45
    ida
    0.44
     تھا
    0.43
     बनवा
    0.43
    POSITIVE LOGITS
    플레이
    0.47
     immer
    0.45
    ფერ
    0.41
     be
    0.41
    愈
    0.40
    女主
    0.39
     embeddings
    0.39
     identifiers
    0.39
     optimistic
    0.38
    助理
    0.38
    Activations Density 0.001%

    No Known Activations