© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8449
    Prev
    Next
    INDEX
    Explanations

    phrases connecting concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cili
    1.13
    ἀ
    1.12
    स्फी
    1.11
    نر
    1.04
    ull
    1.04
    اد
    1.03
     рай
    1.01
    分かる
    1.01
    aan
    0.99
    可能性がある
    0.97
    POSITIVE LOGITS
    jsxFileName
    1.44
    choline
    1.42
    ర
    1.38
     austenite
    1.35
    小說
    1.34
     किया
    1.31
     atrial
    1.31
     ({\
    1.29
     男女
    1.29
    ب
    1.28
    Activations Density 0.000%

    No Known Activations