© 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. 38803
    Prev
    Next
    INDEX
    Explanations

    MAX length, size, or count

    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
     menn
    -1.45
     tradis
    -1.26
     ägg
    -1.26
    撵
    -1.26
    などが
    -1.21
    душка
    -1.19
     antaranya
    -1.16
     raja
    -1.14
    などは
    -1.13
    ೞ
    -1.13
    POSITIVE LOGITS
    During
    1.31
    In
    1.23
    Aside
    1.18
     Previously
    1.18
    Previously
    1.17
    場所で
    1.17
    However
    1.15
    It
    1.14
    為に
    1.13
    変わらず
    1.13
    Activations Density 0.001%

    No Known Activations