© 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. 101992
    Prev
    Next
    INDEX
    Explanations

    langle rangle symbols

    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
    }$
    -3.19
    铼
    -2.66
     Scritto
    -2.45
    1
    -2.44
    ꜆
    -2.41
    if
    -2.41
    越來越
    -2.39
    9
    -2.39
    にほんブログ村
    -2.36
    '
    -2.36
    POSITIVE LOGITS
    ↵
    3.27
     they
    2.89
     
    2.81
    .”
    2.70
     depiction
    2.55
     portátiles
    2.33
    橚
    2.30
    ra
    2.28
    rangle
    2.28
    𐄁
    2.27
    Activations Density 0.003%

    No Known Activations