© 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. 31256
    Prev
    Next
    INDEX
    Explanations

    headlines and headings

    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
    ⠁
    -0.73
     Kare
    -0.73
    weeb
    -0.71
    ţiei
    -0.69
    locus
    -0.69
    kare
    -0.69
     ankaŭ
    -0.68
    деи
    -0.68
     Seat
    -0.68
    edata
    -0.68
    POSITIVE LOGITS
     headline
    6.09
     headlines
    4.81
    headline
    4.50
    Headline
    4.16
     Headline
    3.98
     Headlines
    3.14
     heading
    2.78
     header
    2.63
    heading
    2.50
     headings
    2.36
    Activations Density 0.092%

    No Known Activations