© 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-65K
    7. 4912
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    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
     enquire
    0.64
    にて
    0.57
     zudem
    0.56
     общем
    0.54
    携带
    0.53
     మర
    0.53
    也可
    0.52
    而
    0.52
     acompaña
    0.52
     అందుకే
    0.52
    POSITIVE LOGITS
     Apparently
    0.88
     Specifically
    0.78
    Apparently
    0.74
     Whenever
    0.74
     It
    0.68
     Seriously
    0.68
     Particularly
    0.67
     Instead
    0.67
     Especially
    0.66
    apparently
    0.66
    Activations Density 0.008%

    No Known Activations