© 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. 1603
    Prev
    Next
    INDEX
    Explanations

    who followed by verbs

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

    who followed by a verb

    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
    on
    0.66
    ع
    0.56
    for
    0.55
    ين
    0.53
    ام
    0.52
    ना
    0.52
    分為
    0.51
     bevat
    0.50
    ется
    0.49
    ش
    0.49
    POSITIVE LOGITS
     who
    0.63
     quien
    0.54
    热爱
    0.54
     কিনা
    0.51
     dikutip
    0.51
    lund
    0.47
    한테
    0.47
    যারা
    0.46
     mucha
    0.45
     worshipped
    0.44
    Activations Density 0.153%

    No Known Activations