© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11544
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

    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
     and
    -1.46
     semua
    -1.41
     demás
    -1.21
     tutto
    -1.20
     where
    -1.20
    Ruj
    -1.19
    睢
    -1.19
    diseño
    -1.19
     with
    -1.18
     which
    -1.16
    POSITIVE LOGITS
    ⡯
    1.45
     femininos
    1.37
    Rptr
    1.28
     religiosos
    1.28
    INGREDIENTES
    1.27
    鱻
    1.26
     давно
    1.25
     ของ
    1.24
    DESCRIPCIÓN
    1.24
    SOBRE
    1.20
    Activations Density 0.008%

    No Known Activations