© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15459
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
     but
    -1.41
     нещо
    -1.16
     різних
    -1.14
    licante
    -1.11
     something
    -1.10
    }$$
    -1.07
     things
    -1.06
     Configuración
    -1.04
    edere
    -1.02
     двох
    -1.01
    POSITIVE LOGITS
    旎
    0.98
    筈
    0.93
     エコ
    0.90
    凄く
    0.89
    ∭
    0.88
    おきます
    0.88
    性が
    0.88
    伟大
    0.87
    вший
    0.85
     می‌باشد
    0.85
    Activations Density 0.003%

    No Known Activations