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. 241116
    Prev
    Next
    INDEX
    Explanations

    specific concepts

    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
     कथा
    0.61
    Mono
    0.59
    Associ
    0.56
    mushroom
    0.55
    Network
    0.54
    Mother
    0.54
    豌
    0.54
    Maz
    0.53
     эпизо
    0.53
    Means
    0.53
    POSITIVE LOGITS
     baisse
    0.63
     calcS
    0.60
     নির্ধার
    0.60
     مهمه
    0.58
    नियां
    0.57
     clickView
    0.56
    櫈
    0.55
     metus
    0.55
     minerales
    0.55
     করছে
    0.55
    Activations Density 0.000%

    No Known Activations