© 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. 75222
    Prev
    Next
    INDEX
    Explanations

    bonus, boost, gives

    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
     In
    -1.58
    in
    -1.39
    s
    -1.36
    ate
    -1.34
    il
    -1.31
    <td>
    -1.29
     کرنے
    -1.29
     jeho
    -1.25
    ּוֹ
    -1.23
    pl
    -1.16
    POSITIVE LOGITS
    rapport
    1.40
     Baumwolle
    1.37
     itinéraires
    1.25
     aiuta
    1.20
    Exemple
    1.20
     다른
    1.20
    Ici
    1.20
     يساعد
    1.19
    Président
    1.19
    Groet
    1.19
    Activations Density 0.025%

    No Known Activations