© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117100
    Prev
    Next
    INDEX
    Explanations

    dagger documentation

    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
     Februari
    -0.76
    YNAMICS
    -0.74
    élien
    -0.73
    ét
    -0.73
    ట్
    -0.71
     vira
    -0.71
     borealis
    -0.70
    erg
    -0.70
     циф
    -0.69
     kimi
    -0.69
    POSITIVE LOGITS
     dagger
    0.99
     Dagger
    0.83
    avía
    0.80
    |=\
    0.79
     Supporters
    0.78
     Darcy
    0.77
     ambientale
    0.77
    dena
    0.75
    Kilde
    0.75
    cheibe
    0.75
    Activations Density 0.001%

    No Known Activations