© 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. 187690
    Prev
    Next
    INDEX
    Explanations

    your choice

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

    describing specific concepts

    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
    对此
    0.54
    ล
    0.51
    нор
    0.49
    ہ
    0.49
    լ
    0.49
    瞍
    0.49
    ﺤ
    0.47
    łoś
    0.46
    ozat
    0.46
    <unused264>
    0.46
    POSITIVE LOGITS
    Authenticate
    0.43
     IRAS
    0.43
     CSU
    0.43
     imen
    0.43
     satisfied
    0.41
     Specifies
    0.41
    tsi
    0.41
     Saturday
    0.40
     rifle
    0.40
    lices
    0.40
    Activations Density 0.001%

    No Known Activations