© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112844
    Prev
    Next
    INDEX
    Explanations

    converting or transforming

    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
    стойчи
    -1.58
     but
    -1.31
    ers
    -1.30
    š
    -1.30
    ah
    -1.28
     de
    -1.28
     to
    -1.28
    gs
    -1.22
    ↵↵
    -1.21
    og
    -1.21
    POSITIVE LOGITS
     the
    1.63
     lamenta
    1.40
    Teraz
    1.34
     censo
    1.31
     rapidement
    1.31
     rapidamente
    1.30
    samt
    1.30
    というわけで
    1.27
    雰
    1.27
     récemment
    1.26
    Activations Density 0.222%

    No Known Activations