© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 4996
    Prev
    Next
    INDEX
    Explanations

    deeper into aspect

    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
     arbitrary
    0.77
    spiration
    0.73
    原生
    0.72
    spired
    0.70
     произво
    0.69
    声を
    0.69
    मौ
    0.67
    ύ
    0.67
    iply
    0.67
     ơi
    0.66
    POSITIVE LOGITS
     aspect
    1.00
     alguns
    0.99
     aspectos
    0.99
     aspetti
    0.98
     somew
    0.97
     Aspects
    0.97
     kanske
    0.94
     aspekt
    0.92
     aspects
    0.92
     algumas
    0.91
    Activations Density 0.017%

    No Known Activations