Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 4582
    Prev
    Next
    INDEX
    Explanations

    specifying by comma

    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_65k_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
     olyan
    0.73
    ὧ
    0.73
     প্রভৃতি
    0.72
    ἃ
    0.71
     verschied
    0.70
     इत्यादी
    0.69
     など
    0.67
     ireo
    0.67
     relational
    0.67
     dimers
    0.66
    POSITIVE LOGITS
    ,
    1.60
    യായ
    1.37
     یعنی
    1.30
     namely
    1.29
     yaitu
    1.28
    ،
    1.23
     yakni
    1.18
     iaitu
    1.16
    ,--
    1.13
    である
    1.13
    Activations Density 0.387%

    No Known Activations