© 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. 106460
    Prev
    Next
    INDEX
    Explanations

    settings and configuration

    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
    lagte
    -0.86
     Laravel
    -0.83
    WebMethod
    -0.81
     multiplayer
    -0.81
    OnClick
    -0.76
     Xbox
    -0.75
     UITextField
    -0.75
    ombras
    -0.75
    ∞
    -0.74
    WebApplication
    -0.73
    POSITIVE LOGITS
     preferences
    1.62
     Preferences
    1.35
     preference
    1.23
    preferences
    1.19
     Preference
    1.13
     personalization
    1.12
     personalize
    1.09
    preference
    1.08
     prefs
    1.07
     preferencias
    1.06
    Activations Density 0.109%

    No Known Activations