© 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. 107378
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    ἃ
    -0.81
    orges
    -0.76
     crack
    -0.76
     STRATEG
    -0.76
    eders
    -0.73
    舖
    -0.73
     vanille
    -0.71
     wöch
    -0.71
    たとえば
    -0.71
    ᧐
    -0.71
    POSITIVE LOGITS
     oceans
    0.83
     noite
    0.82
     привле
    0.82
    attempt
    0.81
     attempt
    0.81
    の位置
    0.80
     intentions
    0.80
    ตัว
    0.79
    rani
    0.76
     Wikispecies
    0.75
    Activations Density 0.009%

    No Known Activations