© 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. 65385
    Prev
    Next
    INDEX
    Explanations

    not applicable or available

    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
     simpan
    -1.39
    bagian
    -1.19
    lamak
    -1.17
    jours
    -1.16
     zdarma
    -1.14
     İlk
    -1.13
    ǰ
    -1.12
     Eğ
    -1.09
     tombé
    -1.09
     Tanpa
    -1.09
    POSITIVE LOGITS
     hierzu
    1.30
     ausdrücklich
    1.28
    ↵↵↵↵↵↵↵↵
    1.24
    但却
    1.20
    ↵↵↵
    1.16
    广西
    1.15
    虽说
    1.15
    </sup>
    1.15
    ↵↵↵↵↵
    1.14
    or
    1.13
    Activations Density 0.001%

    No Known Activations