© 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. 2331
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by determiners

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

    within the bounds

    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
     postérieures
    0.25
     omdat
    0.23
    itabbo
    0.23
     त्यानंतर
    0.22
     UNNEEDED
    0.22
     plufieurs
    0.22
     ၂
    0.22
     benutzen
    0.21
     ponieważ
    0.21
     如果
    0.21
    POSITIVE LOGITS
     the
    0.42
     a
    0.33
    the
    0.32
     this
    0.24
    The
    0.24
    ip
    0.21
     The
    0.21
    ende
    0.20
    un
    0.20
     their
    0.19
    Activations Density 0.672%

    No Known Activations