© 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. 457
    Prev
    Next
    INDEX
    Explanations

    certain prepositional phrases

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

    certain specific

    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
     ambos
    0.46
     للنساء
    0.44
    မ္
    0.44
    両
    0.43
     இருவரும்
    0.43
     iki
    0.41
     المسافه
    0.41
    zwischen
    0.41
    female
    0.40
     両
    0.40
    POSITIVE LOGITS
    某个
    1.43
    某些
    1.40
     certain
    1.31
    某一
    1.30
    某
    1.22
     certains
    1.20
     certaines
    1.20
     ciertos
    1.13
     bepaalde
    1.13
     ciertas
    1.12
    Activations Density 0.659%

    No Known Activations