© 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. 46302
    Prev
    Next
    INDEX
    Explanations

    verbs followed by to

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

    beginning actions

    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
     masih
    0.55
     mỗi
    0.52
     została
    0.52
     is
    0.51
    ยัง
    0.50
    SPOT
    0.50
     were
    0.50
     !
    0.49
    ร็จ
    0.49
     punya
    0.48
    POSITIVE LOGITS
    ლ
    0.52
     понимать
    0.50
    g
    0.50
     Comenz
    0.49
     hexagons
    0.48
     pensar
    0.45
    詆
    0.44
    gv
    0.44
    用
    0.44
     comienzan
    0.44
    Activations Density 0.050%

    No Known Activations