© 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. 34-GEMMASCOPE-RES-131K
    7. 31423
    Prev
    Next
    INDEX
    Explanations

    single, one, unified

    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_34/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
     gosta
    -0.88
     lembra
    -0.87
    手紙
    -0.85
    咴
    -0.84
     estaría
    -0.82
    実感
    -0.82
    گوشی
    -0.81
     Edward
    -0.81
    內的
    -0.81
     its
    -0.80
    POSITIVE LOGITS
     unified
    1.57
    统一
    1.44
    統一
    1.37
    unified
    1.30
    Unified
    1.30
     unifying
    1.16
     unify
    1.08
     einheit
    1.03
     consolidated
    1.00
    UNIFIED
    0.99
    Activations Density 0.076%

    No Known Activations