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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 15232
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     doped
    1.36
     فيلم
    1.32
     อ่า
    1.31
     Properties
    1.30
    一定是
    1.22
    掛
    1.21
     দুদকের
    1.20
     temperatures
    1.19
    উন্ট
    1.18
    არ
    1.18
    POSITIVE LOGITS
    슥
    1.72
    主義
    1.58
    cule
    1.55
    PrivateRoute
    1.51
    Ⅽ
    1.48
    gist
    1.48
    abilitas
    1.47
    τρο
    1.43
    Ꮯ
    1.42
    Ϝ
    1.42
    Activations Density 0.000%

    No Known Activations