© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 15351
    Prev
    Next
    INDEX
    Explanations

    Psychology Today blog articles

    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
     symmetrically
    0.67
    텔
    0.66
    expand
    0.64
     volonté
    0.63
     expand
    0.62
    ியது
    0.61
    었던
    0.61
    шими
    0.61
     ..
    0.61
    ヮ
    0.61
    POSITIVE LOGITS
    Milliseconds
    0.76
    henti
    0.71
     बिग
    0.70
     posti
    0.70
     bienestar
    0.68
    জিট
    0.68
    Blur
    0.68
    Blocked
    0.67
    เภท
    0.66
     ثلاثه
    0.65
    Activations Density 0.000%

    No Known Activations