© 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. 105288
    Prev
    Next
    INDEX
    Explanations

    *- Mode: X;

    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
    }
    -1.81
     yanı
    -1.80
     çeşitli
    -1.74
    🪬
    -1.69
     firmado
    -1.69
     vivimos
    -1.66
     genellikle
    -1.64
     but
    -1.64
     özellikle
    -1.63
     plethora
    -1.63
    POSITIVE LOGITS
     GETTING
    1.89
    m
    1.88
    cestor
    1.78
    9
    1.70
    The
    1.70
     следующий
    1.65
    และ
    1.63
    You
    1.63
     și
    1.62
    唐揚げ
    1.62
    Activations Density 0.020%

    No Known Activations