© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11258
    Prev
    Next
    INDEX
    Explanations

    zu + infinitive verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    匐
    2.74
    ecimiento
    2.71
     jScrollPane
    2.63
    ből
    2.63
    ického
    2.59
    tea
    2.59
    ective
    2.46
    ukiy
    2.46
    tho
    2.45
    tha
    2.44
    POSITIVE LOGITS
    s
    3.81
    ات
    2.74
    를
    2.73
    ت
    2.61
    ಯಲ್ಲಿ
    2.58
          
    2.56
    ୀ
    2.50
    ل
    2.38
     די
    2.38
     ber
    2.36
    Activations Density 0.001%

    No Known Activations