© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27061
    Prev
    Next
    INDEX
    Explanations

    citation numbering and structure

    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
     無地
    -1.01
    Abre
    -0.93
    ほんとに
    -0.92
    ButtonModule
    -0.89
     lucru
    -0.88
    ρός
    -0.88
    OTP
    -0.87
    逡
    -0.84
    ELESS
    -0.82
    duire
    -0.82
    POSITIVE LOGITS
     his
    0.88
     minOccurs
    0.86
    Dependent
    0.85
    𝑦
    0.83
     admire
    0.83
    0.83
    雪
    0.82
     ט
    0.81
    his
    0.79
    </b>
    0.79
    Activations Density 0.109%

    No Known Activations