© 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. 84102
    Prev
    Next
    INDEX
    Explanations

    high magnifications / rates / values / density

    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
     "../../../../
    -1.50
    gouv
    -1.46
    provided
    -1.45
    となっている
    -1.41
    partly
    -1.39
     jezt
    -1.38
     a
    -1.37
    ८
    -1.37
     organes
    -1.36
     \
    -1.33
    POSITIVE LOGITS
    8
    1.52
     (>
    1.51
     high
    1.36
     neuen
    1.34
     need
    1.34
     cantora
    1.33
    много
    1.30
    fiques
    1.30
     will
    1.30
     allow
    1.27
    Activations Density 0.225%

    No Known Activations