© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85937
    Prev
    Next
    INDEX
    Explanations

    building or strengthening systems

    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
     or
    -2.55
    日発売
    -1.53
     (
    -1.45
    Many
    -1.40
     at
    -1.34
     including
    -1.34
     with
    -1.32
     bijvoorbeeld
    -1.30
     dokonce
    -1.28
    Often
    -1.27
    POSITIVE LOGITS
     definitiv
    1.65
    簠
    1.58
    weren
    1.44
     aseguró
    1.43
     verhind
    1.40
    داشت
    1.38
     côtes
    1.38
     devoirs
    1.38
     céu
    1.37
     flexibel
    1.37
    Activations Density 0.601%

    No Known Activations