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. 7856
    Prev
    Next
    INDEX
    Explanations

    bachelor of arts degrees

    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
    ੀਆਂ
    1.93
     `:`,
    1.85
    ocrates
    1.82
    
    1.78
    ٺ
    1.78
    ributedString
    1.76
     °,
    1.76
    sect
    1.73
     IQR
    1.73
     الحال
    1.64
    POSITIVE LOGITS
    y
    2.00
    ی
    1.79
    tac
    1.69
     объявления
    1.58
    ic
    1.47
     pokok
    1.44
    дә
    1.40
    comedy
    1.40
     ут
    1.37
     Herzen
    1.36
    Activations Density 0.000%

    No Known Activations