© 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. 34-GEMMASCOPE-RES-131K
    7. 58056
    Prev
    Next
    INDEX
    Explanations

    path components

    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_34/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
    اف
    -0.95
     plethora
    -0.93
     on
    -0.91
     if
    -0.88
    的有
    -0.88
     because
    -0.87
     (
    -0.86
     Италии
    -0.86
     strangers
    -0.86
    ých
    -0.85
    POSITIVE LOGITS
    ⸺
    1.23
     speziellen
    1.21
    (>
    1.17
     aparência
    1.15
     umgangssprach
    1.13
    …(
    1.13
    Composición
    1.11
    mercial
    1.11
     lavable
    1.09
     individuellen
    1.09
    Activations Density 0.027%

    No Known Activations