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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8102
    Prev
    Next
    INDEX
    Explanations

    sets of

    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
    り
    1.17
    േ
    1.15
    거나
    1.11
    াং
    1.05
    м
    1.01
    െ
    1.00
    حي
    0.98
    ה
    0.97
    ै
    0.93
     बचना
    0.90
    POSITIVE LOGITS
    时长
    1.37
    స్కీ
    1.37
    quests
    1.36
     étages
    1.34
    yes
    1.34
     orbits
    1.33
    ques
    1.32
    šta
    1.32
     tutoring
    1.31
    seti
    1.30
    Activations Density 0.011%

    No Known Activations