© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4514
    Prev
    Next
    INDEX
    Explanations

    crisis text line support

    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
     internally
    0.70
     interposed
    0.67
     commented
    0.65
     switching
    0.63
    鰓
    0.61
     داره
    0.61
     interno
    0.60
     remarked
    0.60
     Lenny
    0.60
     знал
    0.59
    POSITIVE LOGITS
    स्टिक
    0.79
     growth
    0.69
    wood
    0.68
     צ
    0.67
     Place
    0.67
     deel
    0.67
     نم
    0.66
     bers
    0.66
     ص
    0.66
    Wood
    0.66
    Activations Density 0.061%

    No Known Activations