© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3981
    Prev
    Next
    INDEX
    Explanations

    particularly/especially those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     इत्यादि
    1.06
    etc
    0.97
     &
    0.89
    Similarly
    0.87
     Etc
    0.84
    或其他
    0.84
     Similarly
    0.82
     yada
    0.82
    Every
    0.81
    ＆
    0.81
    POSITIVE LOGITS
     those
    2.37
    those
    1.98
     ceux
    1.70
     during
    1.60
     quelli
    1.58
     celles
    1.56
     těch
    1.55
     aquellos
    1.48
     aqueles
    1.46
     aquelas
    1.44
    Activations Density 0.502%

    No Known Activations