© 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. 581
    Prev
    Next
    INDEX
    Explanations

    concepts preceding prepositions

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

    support and opportunities for

    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
     are
    0.27
     v
    0.23
     GU
    0.23
     تے
    0.21
     ****",
    0.20
     cheese
    0.20
    v
    0.20
     sono
    0.20
     offering
    0.19
     (-
    0.19
    POSITIVE LOGITS
    于
    0.31
    ให้กับ
    0.26
     kepada
    0.24
    Teri
    0.24
     для
    0.22
    於
    0.22
    ForSettings
    0.22
     درباره
    0.22
    트
    0.22
    для
    0.22
    Activations Density 0.861%

    No Known Activations