© 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. 128580
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    ってました
    -1.41
     évé
    -1.38
    書の
    -1.30
     lavadora
    -1.22
     étanche
    -1.20
    siębior
    -1.18
     rústico
    -1.13
    者に
    -1.12
    şek
    -1.12
    ΠΕ
    -1.10
    POSITIVE LOGITS
     (_)
    1.20
     *++
    1.16
    Principales
    1.14
     ∞
    1.13
    見えます
    1.13
    Torna
    1.11
    ᡴ
    1.11
    楽しめる
    1.11
    などを
    1.10
     рецепта
    1.10
    Activations Density 0.007%

    No Known Activations