© 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. 15634
    Prev
    Next
    INDEX
    Explanations

    examples, for, besides

    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
     which
    -1.69
     которые
    -1.41
    <bos>
    -1.41
     because
    -1.34
    だからこそ
    -1.19
    つまり
    -1.16
    ซึ่ง
    -1.16
    があり
    -1.15
    がなく
    -1.14
    そして
    -1.13
    POSITIVE LOGITS
     along
    1.05
    ändert
    1.05
    為に
    1.05
    ⎩
    1.05
    Zi
    1.03
    }
    1.02
    えっ
    1.02
    ときは
    1.02
    に変更
    1.00
    ところに
    0.99
    Activations Density 0.023%

    No Known Activations