© 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. 9000
    Prev
    Next
    INDEX
    Explanations

    assessing conditions or 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
    probably
    -1.94
     probablement
    -1.65
     probabilmente
    -1.60
    taya
    -1.59
    possibly
    -1.53
     možná
    -1.48
    almost
    -1.45
     choisis
    -1.45
    ksi
    -1.44
     mauva
    -1.44
    POSITIVE LOGITS
     or
    3.81
     any
    3.11
     there
    1.98
     with
    1.95
     still
    1.81
    有任何
    1.78
     now
    1.78
     continues
    1.70
     also
    1.61
     as
    1.59
    Activations Density 0.738%

    No Known Activations