© 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. 84429
    Prev
    Next
    INDEX
    Explanations

    steel and iron objects

    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
    ꯶
    -1.38
    臯
    -1.32
    恭喜
    -1.32
     volumen
    -1.31
     แท
    -1.29
    enced
    -1.27
    个数
    -1.27
    镦
    -1.24
    Trou
    -1.22
    uming
    -1.21
    POSITIVE LOGITS
     This
    1.76
     komplette
    1.48
     Where
    1.36
     selalu
    1.34
     gleiche
    1.30
     alberga
    1.26
     also
    1.22
     It
    1.22
    蟜
    1.21
    odorant
    1.20
    Activations Density 0.063%

    No Known Activations