© 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. 130228
    Prev
    Next
    INDEX
    Explanations

    compound indicators

    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
     those
    -1.27
     this
    -1.25
     it
    -1.23
     what
    -1.14
    翳
    -1.09
     yesterday
    -1.07
     wybrać
    -1.06
     would
    -1.03
     all
    -1.02
    quela
    -1.02
    POSITIVE LOGITS
     санкт
    1.30
    Ruju
    1.23
    Irak
    1.16
    ふと
    1.16
    Reak
    1.16
    Moin
    1.16
    بسم
    1.12
    TryDecode
    1.11
    ēt
    1.10
    あー
    1.10
    Activations Density 0.000%

    No Known Activations