© 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. 34126
    Prev
    Next
    INDEX
    Explanations

    correspondence and author information

    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
    邶
    -1.20
     deſt
    -1.19
     deviennent
    -1.19
    ኗ
    -1.16
     donnent
    -1.14
    ୬
    -1.13
    раздо
    -1.11
    퐶
    -1.09
     Olímpicos
    -1.09
    vaient
    -1.09
    POSITIVE LOGITS
     at
    1.34
    email
    1.34
     email
    1.30
    儘
    1.17
    mailto
    1.17
     discernible
    1.14
     undeniably
    1.13
     with
    1.06
     revital
    1.06
    '
    1.05
    Activations Density 0.005%

    No Known Activations