© 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. 129169
    Prev
    Next
    INDEX
    Explanations

    S/Z prefixes

    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
    this
    -2.83
    This
    -2.44
    owania
    -2.34
    ቍ
    -2.31
    an
    -2.22
    ıyla
    -2.13
    鹟
    -2.13
    喈
    -2.13
    
    -2.11
    ⩴
    -2.11
    POSITIVE LOGITS
    蟶
    2.81
    哙
    2.78
     piensan
    2.38
    O
    2.36
     aseguran
    2.28
     umgeben
    2.22
    袛
    2.20
    前来
    2.16
    grandchildren
    2.16
     ANY
    2.11
    Activations Density 0.009%

    No Known Activations