© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81570
    Prev
    Next
    INDEX
    Explanations

    bolded headings and disclaimers

    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
     '
    -1.09
     berupa
    -1.06
    ----------------
    -1.05
    कु
    -1.02
    namese
    -0.98
    AppCompatTheme
    -0.97
     posee
    -0.94
    なる
    -0.93
    良好的
    -0.90
    一一
    -0.88
    POSITIVE LOGITS
    .**
    1.57
    :**
    1.34
    kwargs
    1.31
    ,**
    1.30
    However
    1.30
    .***
    1.17
    Although
    1.15
     décé
    1.15
    )**
    1.14
     détru
    1.14
    Activations Density 0.043%

    No Known Activations