© 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. 34-GEMMASCOPE-RES-131K
    7. 38625
    Prev
    Next
    INDEX
    Explanations

    academic papers and presentations

    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
    NewLine
    -0.80
    えもん
    -0.73
    about
    -0.73
     য
    -0.68
     查询
    -0.68
     մ
    -0.67
     estés
    -0.66
    aup
    -0.66
     entrevista
    -0.66
     היי
    -0.66
    POSITIVE LOGITS
     paper
    4.19
     papers
    3.73
    paper
    3.09
    Paper
    3.09
     Paper
    2.92
     Papers
    2.55
    papers
    2.53
     PAPER
    2.42
    Papers
    2.41
    PAPER
    2.31
    Activations Density 0.039%

    No Known Activations