© 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. 102792
    Prev
    Next
    INDEX
    Explanations

    retail piece, loss of limbs, from sins

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

    specific marker "<!--Two"

    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
    insights
    0.54
    φαι
    0.52
    h
    0.51
     autoestima
    0.50
    hx
    0.48
    utc
    0.48
    arey
    0.48
     felicidad
    0.47
    argument
    0.47
    adim
    0.47
    POSITIVE LOGITS
    DLE
    0.50
     ROS
    0.49
     Preferences
    0.46
     Reservation
    0.46
    优
    0.46
    Reservation
    0.45
     Numer
    0.44
     Cromwell
    0.44
    ENT
    0.44
     COME
    0.43
    Activations Density 0.000%

    No Known Activations