© 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. 15611
    Prev
    Next
    INDEX
    Explanations

    time periods and sequences

    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
     allerede
    -1.13
    Ṛ
    -1.10
     relojes
    -1.03
    ignment
    -1.02
    gered
    -0.99
     and
    -0.97
    genen
    -0.94
     polaire
    -0.93
     secr
    -0.92
    Final
    -0.91
    POSITIVE LOGITS
     подряд
    1.34
    <bos>
    1.27
     irmão
    1.24
    では
    1.22
     ago
    1.17
    氾
    1.12
    Contd
    1.11
    álně
    1.09
    における
    1.08
     deixou
    1.06
    Activations Density 0.037%

    No Known Activations