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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 173109
    Prev
    Next
    INDEX
    Explanations

    nod your head

    np_acts-logits-general · gemini-2.5-flash-lite

    leaders often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rougeâtres
    0.50
     Bhagavata
    0.50
    قیع
    0.50
    썽
    0.47
     Bosnia
    0.45
    Iraq
    0.44
     अब्दुल
    0.44
    จะ
    0.43
     είναι
    0.43
    спользова
    0.43
    POSITIVE LOGITS
     установ
    0.48
    £
    0.46
    撸
    0.46
    tg
    0.45
    变更
    0.45
    lld
    0.43
     RELEASE
    0.43
     illicit
    0.43
     REPORT
    0.43
     release
    0.42
    Activations Density 0.001%

    No Known Activations