© 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. 58
    Prev
    Next
    INDEX
    Explanations

    information requests and records

    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
     -
    -1.43
    :
    -1.42
     −
    -1.37
    鞏
    -1.32
     guerr
    -1.30
    土産
    -1.21
    There
    -1.21
    </h2>
    -1.20
     péché
    -1.20
     on
    -1.18
    POSITIVE LOGITS
     crescere
    1.56
     garanzia
    1.49
     needed
    1.47
    氽
    1.46
     musíte
    1.45
     capitolo
    1.44
    姤
    1.41
    歺
    1.40
     cammino
    1.40
     dedicato
    1.40
    Activations Density 0.044%

    No Known Activations