© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44765
    Prev
    Next
    INDEX
    Explanations

    plus précisément

    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
     personnalisées
    -2.61
     Owing
    -2.39
     Âge
    -2.33
     spéciales
    -2.31
    女兒
    -2.28
     adaptées
    -2.28
    While
    -2.27
    We
    -2.27
     substantiate
    -2.27
     Notwithstanding
    -2.25
    POSITIVE LOGITS
     they
    2.58
    <td>
    2.52
    忆
    2.39
     \
    2.31
     is
    2.31
    <bos>
    2.31
    敍
    2.30
     his
    2.28
    ᨁ
    2.27
     '/':
    2.23
    Activations Density 0.002%

    No Known Activations