© 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. 52606
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating direction or location

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

    incorporating into the

    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
     мили
    0.46
     уены
    0.45
     пробу
    0.44
     хан
    0.44
    逋
    0.44
     ошиб
    0.43
    粡
    0.43
     SKAction
    0.43
    ᒃ
    0.42
    忔
    0.42
    POSITIVE LOGITS
    1
    0.52
    na
    0.50
     to
    0.48
    ni
    0.47
    2
    0.47
     yang
    0.46
    der
    0.45
    0.44
     gon
    0.44
    di
    0.44
    Activations Density 0.001%

    No Known Activations