© 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. 22-GEMMASCOPE-2-RES-262K
    4. 6163
    Prev
    Next
    INDEX
    Explanations

    stylized image or graphic

    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_22_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
    ی
    1.06
     tip
    1.04
    袬
    1.01
    Dónde
    1.00
    लिए
    0.99
    colato
    0.99
    spaceBetween
    0.94
    臤
    0.94
    во
    0.94
     spus
    0.93
    POSITIVE LOGITS
    ized
    1.14
    SO
    1.10
    RuntimeException
    1.05
     memoir
    1.05
     Club
    0.98
     Decomposition
    0.97
    "(
    0.97
    ట్
    0.94
     Ironically
    0.93
     Cinem
    0.93
    Activations Density 0.001%

    No Known Activations