© 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. 78174
    Prev
    Next
    INDEX
    Explanations

    advice and questions about personal situations

    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
     xay
    -1.09
    都需要
    -1.05
    跆
    -1.04
     respectful
    -1.02
    もあり
    -0.99
    ic
    -0.98
    मित
    -0.97
     powod
    -0.95
     возможность
    -0.95
     AssemblyCulture
    -0.95
    POSITIVE LOGITS
     your
    1.65
    ığınız
    1.32
    為了
    1.24
    sä
    1.24
    María
    1.17
     Internasional
    1.17
     yourself
    1.16
     ‌
    1.13
    寶寶
    1.13
    rootView
    1.10
    Activations Density 0.088%

    No Known Activations