© 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. 13885
    Prev
    Next
    INDEX
    Explanations

    emerging and rising talents

    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
    扨
    -1.52
    餽
    -1.41
     metus
    -1.38
    <bos>
    -1.35
     utilisée
    -1.34
    paisaje
    -1.34
     ondu
    -1.30
     royal
    -1.30
     bascul
    -1.30
     vano
    -1.30
    POSITIVE LOGITS
     \
    1.49
     centimetres
    1.35
    ceptable
    1.32
     perangkat
    1.31
    ikiran
    1.30
     This
    1.27
    Алек
    1.26
    Verso
    1.26
     أعلام
    1.24
    🦱
    1.24
    Activations Density 0.025%

    No Known Activations