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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 240865
    Prev
    Next
    INDEX
    Explanations

    technical and specific context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     анг
    0.59
     verdadero
    0.59
     libro
    0.59
    qst
    0.58
     Qualquer
    0.58
     livro
    0.56
     Baill
    0.56
    朿
    0.56
     libros
    0.55
     eigentlich
    0.55
    POSITIVE LOGITS
    主动
    0.64
     situational
    0.64
    edad
    0.63
     کردار
    0.60
    MODULE
    0.59
    ęcz
    0.58
    resi
    0.57
     زده
    0.57
    AVOA
    0.57
    േഷ
    0.57
    Activations Density 0.001%

    No Known Activations