© 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. 128420
    Prev
    Next
    INDEX
    Explanations

    comment, ddI, ddY

    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
     одной
    -1.75
    𝟎
    -1.43
    Zdroj
    -1.41
            
    -1.40
    ("
    -1.36
    Including
    -1.32
     Kemudian
    -1.30
     Sebagai
    -1.28
                            
    -1.26
                   
    -1.25
    POSITIVE LOGITS
     that
    1.64
    </h5>
    1.26
     ")");
    1.25
    厝
    1.19
    大家好
    1.19
     copious
    1.18
    웬
    1.18
     вижу
    1.16
     persistently
    1.16
     longtime
    1.16
    Activations Density 0.004%

    No Known Activations