© 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. 157255
    Prev
    Next
    INDEX
    Explanations

    words following "to" or "for"

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

    controls story

    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
     Investor
    0.52
     bermanfaat
    0.46
     Explorer
    0.46
    ie
    0.45
    *.
    0.44
     Visitor
    0.44
     Customer
    0.43
    ».
    0.43
    l
    0.43
    **.
    0.42
    POSITIVE LOGITS
     ake
    0.50
    ור
    0.48
     spaceleft
    0.48
    승
    0.47
    량
    0.47
    검
    0.46
    交换
    0.46
     mischiev
    0.46
     trauer
    0.46
    듬
    0.46
    Activations Density 0.005%

    No Known Activations