© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19888
    Prev
    Next
    INDEX
    Explanations

    INSERT INTO statements

    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
     which
    -1.72
     or
    -1.51
     this
    -1.41
     about
    -1.34
     waarmee
    -1.33
     could
    -1.30
    купить
    -1.27
     will
    -1.24
     think
    -1.24
    midt
    -1.23
    POSITIVE LOGITS
     trabajador
    1.36
    SharedCtor
    1.31
    そのような
    1.23
     recenti
    1.22
    Parametros
    1.22
    踱
    1.17
    Loai
    1.17
    MergeFrom
    1.16
    ſten
    1.16
     recente
    1.14
    Activations Density 0.007%

    No Known Activations