© 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. 10-GEMMASCOPE-RES-131K
    7. 11560
    Prev
    Next
    INDEX
    Explanations

    gives thanks or congratulations

    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
    ｷ
    -1.31
     gratuitos
    -1.26
     уже
    -1.25
    nieren
    -1.23
    utdown
    -1.22
    南瓜
    -1.20
    ﾎ
    -1.20
     decorativas
    -1.20
    じゃなくて
    -1.20
     depuis
    -1.18
    POSITIVE LOGITS
    two
    1.57
    </h2>
    1.44
    ors
    1.41
    ates
    1.40
     Zurück
    1.30
    ributing
    1.28
    这一次
    1.28
     respect
    1.24
    still
    1.23
     hope
    1.23
    Activations Density 0.026%

    No Known Activations