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-262K
    4. 19501
    Prev
    Next
    INDEX
    Explanations

    sequence after certain words

    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
    '.
    1.09
    ++.
    1.05
    ا۔
    1.02
    .'
    0.99
    。
    0.99
    _.
    0.97
    °.
    0.97
    }.
    0.95
     ។
    0.93
    !!.
    0.92
    POSITIVE LOGITS
     após
    1.10
     after
    0.97
     después
    0.87
     dopo
    0.86
     після
    0.85
     setelah
    0.84
     après
    0.83
     després
    0.82
     после
    0.81
     μετά
    0.80
    Activations Density 0.001%

    No Known Activations