© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104972
    Prev
    Next
    INDEX
    Explanations

    except when conditions apply

    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
    🤐
    -1.71
     plafon
    -1.67
     kila
    -1.67
     Interne
    -1.65
    antism
    -1.58
     XXXI
    -1.57
     XXIX
    -1.56
     koste
    -1.56
    👿
    -1.55
     XXXIII
    -1.55
    POSITIVE LOGITS
     in
    1.90
     through
    1.85
     from
    1.84
     with
    1.79
     on
    1.67
     kinds
    1.66
    Again
    1.66
     Aussagen
    1.62
     Again
    1.58
     different
    1.57
    Activations Density 0.029%

    No Known Activations