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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 3110
    Prev
    Next
    INDEX
    Explanations

    changes needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_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
    بية
    1.45
    ن
    1.24
     prokary
    1.23
    FileInputExcel
    1.20
     emplacement
    1.18
     siquiera
    1.16
     sommer
    1.16
     anastomosis
    1.16
     visant
    1.14
     этим
    1.13
    POSITIVE LOGITS
    ,
    1.06
     CHANGES
    0.98
    NING
    0.97
    tı
    0.95
    ec
    0.95
    ="/">
    0.92
    }}>
    0.88
     Continued
    0.88
    vstack
    0.87
    서
    0.87
    Activations Density 0.088%

    No Known Activations