© 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. 28276
    Prev
    Next
    INDEX
    Explanations

    I followed by something

    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
     their
    -1.53
     there
    -1.52
     maybe
    -1.48
     its
    -1.40
     without
    -1.30
     with
    -1.28
     related
    -1.23
     where
    -1.22
     or
    -1.20
     any
    -1.20
    POSITIVE LOGITS
    PLEASE
    1.34
     nasional
    1.24
     perpé
    1.20
     signifikan
    1.20
     اللاعب
    1.17
    nship
    1.16
    ఝ
    1.16
    StringUtils
    1.16
     übrigens
    1.15
    乃是
    1.14
    Activations Density 0.051%

    No Known Activations