© 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. 60620
    Prev
    Next
    INDEX
    Explanations

    audience

    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
     гораздо
    -2.84
    咴
    -2.50
     hablaba
    -2.39
     conocía
    -2.34
     inappropriés
    -2.34
    媜
    -2.34
     Entsche
    -2.33
     podía
    -2.31
    }$
    -2.25
    ?"
    -2.25
    POSITIVE LOGITS
    ↵↵
    3.45
    蜮
    2.84
    }
    2.59
    鶿
    2.59
    猹
    2.56
    锝
    2.56
    柃
    2.39
    
    2.38
    孓
    2.36
    providedIn
    2.31
    Activations Density 0.002%

    No Known Activations