© 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. 3935
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

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

    text HOME to 741741

    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
    𒁲
    0.30
     polémica
    0.30
     craindre
    0.29
     criaturas
    0.29
     ennemis
    0.29
    வீன
    0.29
     proizv
    0.28
     suele
    0.28
     montagnes
    0.28
    ټبال
    0.28
    POSITIVE LOGITS
    ↵
    0.44
    \
    0.38
     the
    0.36
     \
    0.35
    ↵↵
    0.34
     (
    0.34
    ；
    0.33
    ,
    0.33
    <eos>
    0.32
    …
    0.31
    Activations Density 0.410%

    No Known Activations