Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8582
    Prev
    Next
    INDEX
    Explanations

    Franco Corelli, All Saints Church

    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
    !
    -1.07
     we
    -1.05
     hypertension
    -1.00
    uuuuu
    -0.98
     whilst
    -0.92
     plethora
    -0.91
    !';
    -0.90
    rrrrrr
    -0.90
    撰
    -0.89
     soir
    -0.88
    POSITIVE LOGITS
    Trusted
    1.71
     Trusted
    1.49
     your
    1.39
     Mitarbeit
    1.25
    your
    1.19
    ˒
    1.16
     buildup
    1.16
    Your
    1.14
     Obtén
    1.14
     Ihrem
    1.10
    Activations Density 0.126%

    No Known Activations