© 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. 68127
    Prev
    Next
    INDEX
    Explanations

    spouse of, him but

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

    weapons, without human intervention

    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
    }`
    0.46
     Gemeinden
    0.46
     noite
    0.45
    Alarm
    0.44
    Grace
    0.44
    私たち
    0.44
    uffy
    0.44
    (
    0.44
    Am
    0.44
    _
    0.43
    POSITIVE LOGITS
    ا۔
    0.54
     procured
    0.50
     stroked
    0.50
     juggling
    0.49
     supplied
    0.49
    通販
    0.48
     protruding
    0.48
     netted
    0.47
     starboard
    0.47
     grounded
    0.46
    Activations Density 0.002%

    No Known Activations