© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130821
    Prev
    Next
    INDEX
    Explanations

    code delimiters 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
     not
    -1.16
     for
    -1.14
    ✨:
    -1.11
     several
    -1.05
     three
    -1.04
     five
    -1.04
     prevent
    -1.02
    ее
    -0.98
     four
    -0.98
     all
    -0.98
    POSITIVE LOGITS
    也可以
    1.26
     パッド
    1.16
    aimeJ
    1.16
    ’;
    1.14
     necessità
    1.14
     coinvol
    1.14
     entraîner
    1.14
    Dati
    1.13
    良し
    1.12
     erhi
    1.10
    Activations Density 0.001%

    No Known Activations