© 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. 113224
    Prev
    Next
    INDEX
    Explanations

    which is

    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
    價格
    -1.51
    Однако
    -1.49
    各種
    -1.48
    がありますが
    -1.45
    pherds
    -1.45
     разнообраз
    -1.44
    
    -1.42
    fiée
    -1.41
     chiare
    -1.39
     What
    -1.38
    POSITIVE LOGITS
    </u>
    1.66
     incluso
    1.57
     even
    1.53
     специально
    1.41
    </strong>
    1.35
     last
    1.34
     todas
    1.32
     especially
    1.31
    atische
    1.30
     las
    1.27
    Activations Density 0.014%

    No Known Activations