© 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. 22-GEMMASCOPE-RES-131K
    7. 15291
    Prev
    Next
    INDEX
    Explanations

    demonstrates or shows evidence

    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_22/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
    Semua
    -1.09
    Kondisi
    -1.05
     Guatem
    -0.94
     consenti
    -0.91
    Bagaimana
    -0.91
    はこんな感じ
    -0.90
    Proses
    -0.88
    ceae
    -0.88
     introd
    -0.87
    Jedis
    -0.85
    POSITIVE LOGITS
     evidenced
    1.25
     even
    1.13
     evident
    1.07
     attested
    0.98
    umerable
    0.98
    cún
    0.90
     plainly
    0.90
     from
    0.90
    那位
    0.90
     anyone
    0.88
    Activations Density 0.021%

    No Known Activations