© 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. 29-GEMMASCOPE-2-RES-262K
    7. 149830
    Prev
    Next
    INDEX
    Explanations

    ar followed by sounds like ca, qu, t, s, b

    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_29_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
     potest
    0.88
     Demonstr
    0.83
    Demon
    0.81
    setBadgeText
    0.81
    ологи
    0.81
    ᓗ
    0.78
     udziel
    0.78
     Cooke
    0.77
     Er
    0.77
     despert
    0.77
    POSITIVE LOGITS
     accessibility
    0.83
     firing
    0.81
     bushing
    0.80
     instrumentality
    0.77
     bushy
    0.76
     stipulation
    0.76
    νοντας
    0.75
     bush
    0.75
    闕
    0.74
     stylesheet
    0.73
    Activations Density 0.001%

    No Known Activations