© 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. 47462
    Prev
    Next
    INDEX
    Explanations

    list items markers

    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
     like
    -0.84
    mma
    -0.83
     concierto
    -0.82
     memas
    -0.79
    袂
    -0.77
    清掃
    -0.76
    ꪻ
    -0.75
     amigas
    -0.74
    遺跡
    -0.74
    elfth
    -0.73
    POSITIVE LOGITS
    色々な
    0.96
    ぉ
    0.91
    色んな
    0.90
     powerfully
    0.89
    创作
    0.89
     наоборот
    0.89
    craina
    0.88
     hugely
    0.88
     déta
    0.88
    ことがある
    0.87
    Activations Density 0.001%

    No Known Activations