© 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. 59691
    Prev
    Next
    INDEX
    Explanations

    How to use

    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
     våra
    -1.27
    因為
    -1.26
     därför
    -1.20
    álně
    -1.16
     нашим
    -1.13
    但是
    -1.12
    "].
    -1.12
     también
    -1.12
     anvä
    -1.11
    }];
    -1.10
    POSITIVE LOGITS
     by
    1.34
    août
    1.23
     možné
    1.17
    Dichloropropane
    1.16
     读
    1.09
     on
    1.06
     зді
    1.05
    attled
    1.05
    честву
    1.05
     sejak
    1.05
    Activations Density 0.196%

    No Known Activations