© 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. 22-GEMMASCOPE-RES-131K
    7. 15917
    Prev
    Next
    INDEX
    Explanations

    static class or %s formatting

    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_22/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
    çok
    -1.01
    indest
    -0.98
    kleber
    -0.91
    ㅂ
    -0.87
    ゚
    -0.84
    ccan
    -0.82
    ピール
    -0.82
    Šalt
    -0.82
    ̂
    -0.82
    您好
    -0.82
    POSITIVE LOGITS
     speak
    0.92
     tetto
    0.88
     sopra
    0.88
     recesses
    0.88
     shouldBe
    0.87
     their
    0.85
    ্স
    0.83
     overcoat
    0.80
     above
    0.80
     by
    0.78
    Activations Density 0.001%

    No Known Activations