© 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. 48535
    Prev
    Next
    INDEX
    Explanations

    bird names and specific nouns

    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
    甞
    -1.69
    雠
    -1.46
    ’
    -1.45
    </strong>
    -1.44
    鹇
    -1.42
     fallecido
    -1.38
    臜
    -1.37
    想了想
    -1.35
     .........
    -1.31
    萏
    -1.31
    POSITIVE LOGITS
    vaders
    1.35
     ")";
    1.30
    Zubereitung
    1.30
     idiot
    1.29
    fraid
    1.25
     /\.(
    1.25
    ెక్
    1.22
     概要
    1.20
     konus
    1.20
    rigation
    1.20
    Activations Density 0.032%

    No Known Activations