© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241579
    Prev
    Next
    INDEX
    Explanations

    NVIDIA Gaza

    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
     Lump
    0.63
     getN
    0.61
     ニ
    0.61
     ..
    0.59
    ėmis
    0.58
    olicy
    0.58
     マイ
    0.57
     น่ะ
    0.57
    蕃
    0.57
     マル
    0.57
    POSITIVE LOGITS
     bouquets
    0.64
     stents
    0.60
     جگ
    0.59
    Izq
    0.57
     dựng
    0.57
     tassels
    0.55
     grooves
    0.54
    hse
    0.54
    与其他
    0.54
     frag
    0.54
    Activations Density 0.000%

    No Known Activations