© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106487
    Prev
    Next
    INDEX
    Explanations

    sign_in, reset, or code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [])
    -0.81
     только
    -0.81
     انتشار
    -0.80
    οντας
    -0.76
     inicia
    -0.75
    setCharacter
    -0.73
    ".
    -0.73
     промо
    -0.72
    \!
    -0.72
    capi
    -0.71
    POSITIVE LOGITS
     remember
    1.21
    remember
    1.00
     Remember
    0.94
    Remember
    0.93
     REMEMBER
    0.90
    Riding
    0.87
     reset
    0.87
    ないけど
    0.85
     riding
    0.84
     Riding
    0.83
    Activations Density 0.005%

    No Known Activations