© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 4648
    Prev
    Next
    INDEX
    Explanations

    names and origins

    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
     throughput
    0.58
     Final
    0.58
     sensitive
    0.57
     해당하는
    0.55
    .):
    0.55
    こだ
    0.54
     Sensitive
    0.53
    ()/
    0.53
     output
    0.53
     (~
    0.53
    POSITIVE LOGITS
     botella
    0.68
    imperial
    0.67
     jardin
    0.64
     lembra
    0.63
     tinha
    0.62
     fazla
    0.62
     secretário
    0.61
    CAG
    0.60
     divertida
    0.59
    Bottle
    0.59
    Activations Density 0.122%

    No Known Activations