© 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. 241344
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
     حیثیت
    0.55
    を用いた
    0.55
    역
    0.54
     Séance
    0.54
    逓
    0.54
    TIMEOUT
    0.52
     什么
    0.52
    থেষ্ট
    0.52
    ŗ
    0.52
    𒐪
    0.52
    POSITIVE LOGITS
    natures
    0.63
    պես
    0.62
     facil
    0.58
     bea
    0.55
     alphanumeric
    0.54
     Natur
    0.53
    Condensed
    0.53
     feathered
    0.53
     alen
    0.53
    nature
    0.53
    Activations Density 0.000%

    No Known Activations