© 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. 22-GEMMASCOPE-RES-131K
    7. 33105
    Prev
    Next
    INDEX
    Explanations

    inquiry and connective phrases

    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_22/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
    corrhi
    -1.70
     you
    -1.41
    に戻
    -1.38
    verture
    -1.37
     condicion
    -1.36
     diferentes
    -1.34
     siempre
    -1.34
     pregunt
    -1.34
     nunca
    -1.32
    ができます
    -1.28
    POSITIVE LOGITS
    そして
    1.29
    おそらく
    1.24
    という感じ
    1.22
     这个
    1.18
     then
    1.17
    と考えて
    1.16
    そのため
    1.13
    と思われます
    1.13
     Grüßen
    1.12
     fusca
    1.12
    Activations Density 0.047%

    No Known Activations