© 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. 34-GEMMASCOPE-RES-131K
    7. 58549
    Prev
    Next
    INDEX
    Explanations

    provided clauses following 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_34/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
     Guatemala
    -0.94
     karma
    -0.91
     because
    -0.88
    ầm
    -0.86
     as
    -0.85
    登場人物
    -0.84
     =[
    -0.81
    karena
    -0.81
     литературы
    -0.81
    Pozdrawiam
    -0.79
    POSITIVE LOGITS
     provided
    2.72
     Provided
    2.67
    Provided
    2.55
    provided
    2.39
     PROVIDED
    2.23
    PROVID
    1.64
    vided
    1.30
     proviso
    1.27
     and
    1.21
     such
    1.12
    Activations Density 0.018%

    No Known Activations