© 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. 8333
    Prev
    Next
    INDEX
    Explanations

    hexadecimal values and bit operations

    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
     are
    -1.64
     make
    -1.41
    ем
    -1.38
     get
    -1.27
     won
    -1.27
     have
    -1.20
     competen
    -1.20
    ꪻ
    -1.20
     Would
    -1.16
    ie
    -1.15
    POSITIVE LOGITS
    </h2>
    1.58
     сделал
    1.50
    狃
    1.45
    玊
    1.44
    schrank
    1.41
     erfolgre
    1.38
    ᅚ
    1.37
     EIGHT
    1.36
     Umständen
    1.35
    '
    1.35
    Activations Density 0.023%

    No Known Activations