© 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. 10-GEMMASCOPE-RES-131K
    7. 101994
    Prev
    Next
    INDEX
    Explanations

    requirements and demands

    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
     Like
    -2.27
    }$,
    -2.13
    Like
    -1.95
     endeavors
    -1.86
     With
    -1.84
    One
    -1.81
    ?”
    -1.81
    　　（
    -1.77
    魚
    -1.77
     Kontext
    -1.75
    POSITIVE LOGITS
     attesa
    2.16
    勦
    2.02
    跸
    1.98
    嶮
    1.95
    皤
    1.91
     añad
    1.87
    ING
    1.85
     requieren
    1.85
    かっこ
    1.78
    虓
    1.77
    Activations Density 0.040%

    No Known Activations