© 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. 133695
    Prev
    Next
    INDEX
    Explanations

    verb or adverb followed by preposition

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

    brief information

    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
     trú
    0.55
     fos
    0.52
     Fos
    0.50
     mér
    0.49
     sơ
    0.48
    仅
    0.48
     ná
    0.48
     접
    0.48
     parab
    0.48
     ví
    0.48
    POSITIVE LOGITS
    Bismillahirrah
    0.52
    ualitas
    0.50
    lobe
    0.48
    fees
    0.47
    osevelt
    0.46
    Deze
    0.45
    Cc
    0.45
    ince
    0.44
    েকে
    0.43
    inesh
    0.43
    Activations Density 0.000%

    No Known Activations