© 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. 10-GEMMASCOPE-RES-131K
    7. 12935
    Prev
    Next
    INDEX
    Explanations

    leading to consequences

    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_10/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
     need
    -1.96
     it
    -1.76
     will
    -1.64
     would
    -1.58
     is
    -1.55
     tetapi
    -1.46
     как
    -1.46
     несмотря
    -1.40
     know
    -1.38
     setelah
    -1.36
    POSITIVE LOGITS
    惴
    1.69
     tissus
    1.63
    ของ
    1.57
    ın
    1.57
     journaliste
    1.55
     wortel
    1.55
    dónde
    1.53
     finalement
    1.53
    ě
    1.52
    尪
    1.49
    Activations Density 0.031%

    No Known Activations