Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12115
    Prev
    Next
    INDEX
    Explanations

    new class names

    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
     its
    -1.54
     their
    -1.48
     have
    -1.46
    子は
    -1.29
     all
    -1.23
     who
    -1.17
    子が
    -1.12
     other
    -1.10
     ア
    -1.08
     each
    -1.06
    POSITIVE LOGITS
    おはよう
    1.20
     cenderung
    1.17
    czywiście
    1.15
     berbasis
    1.10
    Bety
    1.10
    Tils
    1.08
    Fär
    1.08
    Objekt
    1.08
    שלום
    1.07
    Hilsen
    1.07
    Activations Density 0.008%

    No Known Activations