© 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. 74109
    Prev
    Next
    INDEX
    Explanations

    department name or identifier

    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
    Visit
    -1.60
     consulter
    -1.53
     metoda
    -1.53
     constate
    -1.53
    They
    -1.52
     bemerken
    -1.49
     experimente
    -1.47
    䛗
    -1.45
     garantie
    -1.45
     producent
    -1.45
    POSITIVE LOGITS
     if
    1.82
    }
    1.60
     když
    1.43
     when
    1.42
     and
    1.41
     förra
    1.36
     using
    1.36
     within
    1.33
    を描く
    1.32
    šanu
    1.31
    Activations Density 0.010%

    No Known Activations