© 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. 9744
    Prev
    Next
    INDEX
    Explanations

    what a/an

    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
     bellissimo
    -1.69
     by
    -1.46
     medesimo
    -1.45
     capitolo
    -1.45
     dettaglio
    -1.44
     bacio
    -1.39
     peccato
    -1.38
     tempio
    -1.38
     into
    -1.38
    unfortunately
    -1.38
    POSITIVE LOGITS
     they
    1.45
     so
    1.41
     this
    1.40
    これだけ
    1.31
     být
    1.30
    هداف
    1.27
     or
    1.24
    they
    1.21
    瀧
    1.20
     zoveel
    1.20
    Activations Density 0.021%

    No Known Activations