© 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. 22-GEMMASCOPE-RES-131K
    7. 54073
    Prev
    Next
    INDEX
    Explanations

    places and addresses

    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_22/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
    侷
    -1.21
     sierp
    -1.19
    ENCIA
    -1.16
    ﹔
    -1.13
    kově
    -1.13
     ilustraciones
    -1.12
    اتب
    -1.11
     دخترانه
    -1.10
    ないです
    -1.09
    GORITH
    -1.09
    POSITIVE LOGITS
     malattie
    1.09
     of
    1.07
     to
    1.05
     trouve
    1.02
                                   
    1.01
     school
    0.98
     персонал
    0.97
     смог
    0.97
     взгляд
    0.96
    想到
    0.95
    Activations Density 0.010%

    No Known Activations