© 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. 60685
    Prev
    Next
    INDEX
    Explanations

    directions and distances

    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
    ACTED
    -1.65
     jenem
    -1.59
     jener
    -1.59
     justamente
    -1.48
    abbaye
    -1.48
    EVERY
    -1.46
     volando
    -1.46
     никакого
    -1.44
     sentada
    -1.42
     aquellos
    -1.41
    POSITIVE LOGITS
     it
    1.97
     you
    1.84
     the
    1.63
     verpflich
    1.59
     antworte
    1.52
     groundwork
    1.45
     totaling
    1.44
    "
    1.44
    dzić
    1.44
     sehingga
    1.43
    Activations Density 0.008%

    No Known Activations