© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28103
    Prev
    Next
    INDEX
    Explanations

    unsupported or supported

    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
     péro
    -1.28
    が無い
    -1.27
    うわ
    -1.27
     nepiecieš
    -1.24
     a
    -1.23
    ݯ
    -1.21
     médicament
    -1.18
     unſ
    -1.16
    すっ
    -1.16
     bluza
    -1.15
    POSITIVE LOGITS
     at
    1.33
     because
    1.19
     even
    1.16
     даже
    1.15
     during
    1.15
     Even
    1.13
    </tr>
    1.13
    d
    1.11
    l
    1.11
     or
    1.11
    Activations Density 0.015%

    No Known Activations