© 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. 15401
    Prev
    Next
    INDEX
    Explanations

    programming language extensions

    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
    があり
    -1.63
    などを
    -1.42
     tages
    -1.38
     technisch
    -1.35
    を含む
    -1.34
    が
    -1.30
    を
    -1.30
    をはじめ
    -1.30
     Abon
    -1.26
     Aktiv
    -1.25
    POSITIVE LOGITS
    なのかな
    1.45
    に行って
    1.45
     that
    1.43
     traditionally
    1.39
    曩
    1.38
     groter
    1.35
     their
    1.31
     relentlessly
    1.30
     specially
    1.27
    桀
    1.25
    Activations Density 0.099%

    No Known Activations