© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99076
    Prev
    Next
    INDEX
    Explanations

    magnitude and attitude

    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
     Compute
    -0.73
     realiza
    -0.71
     MAUR
    -0.69
    dater
    -0.67
    encing
    -0.66
    hsa
    -0.66
    tivazione
    -0.66
     پای
    -0.65
     гу
    -0.64
     Honig
    -0.63
    POSITIVE LOGITS
    itude
    2.31
     attitude
    2.25
     Attitude
    2.13
    ITUDE
    1.98
    Attitude
    1.94
    attitude
    1.91
    tude
    1.80
    titude
    1.77
    itudes
    1.64
     attitudes
    1.54
    Activations Density 0.046%

    No Known Activations