© 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. 113108
    Prev
    Next
    INDEX
    Explanations

    altogether / altogether too

    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
     tomando
    -2.34
    謦
    -2.27
     buscando
    -2.27
    
    -2.16
     komplette
    -2.14
     realizando
    -2.08
     gebeten
    -2.06
     tą
    -2.00
     vollständige
    -1.98
    </i>
    -1.97
    POSITIVE LOGITS
     There
    2.67
    甡
    2.11
    there
    2.08
     encompassing
    2.05
    quelize
    2.03
    他现在
    2.03
    atother
    2.02
    　　《
    2.00
    ieteur
    1.94
     categorized
    1.91
    Activations Density 0.002%

    No Known Activations