© 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. 91614
    Prev
    Next
    INDEX
    Explanations

    hardware programming constructs

    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
    uesas
    -0.86
    reno
    -0.75
    默默
    -0.74
     cosme
    -0.73
     tengo
    -0.73
     viscose
    -0.71
     achten
    -0.71
    entation
    -0.69
    CAST
    -0.68
    LDAP
    -0.68
    POSITIVE LOGITS
     software
    1.06
     read
    0.94
     Software
    0.93
    Software
    0.92
     enable
    0.92
    enable
    0.83
    software
    0.80
     Poll
    0.79
    mR
    0.77
     stop
    0.77
    Activations Density 0.009%

    No Known Activations