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. 7346
    Prev
    Next
    INDEX
    Explanations

    book in advance to skip lines

    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
    ]";
    0.82
    itling
    0.72
    ದ್ರ
    0.71
    zechoslovak
    0.71
    UGIN
    0.70
    歉
    0.70
    swering
    0.69
     வாழ்
    0.69
     transistor
    0.69
    IONES
    0.68
    POSITIVE LOGITS
    Officials
    0.76
     looms
    0.74
    Những
    0.71
     کم
    0.69
     туристов
    0.69
     memang
    0.69
     Luckily
    0.68
    Tres
    0.67
    𝐠
    0.67
     detract
    0.67
    Activations Density 0.090%

    No Known Activations