© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82227
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    成交
    0.40
    最大
    0.40
    casted
    0.39
    ership
    0.38
     uveden
    0.38
    化
    0.38
     privately
    0.38
     multiplied
    0.37
    最
    0.37
    ება
    0.37
    POSITIVE LOGITS
     garantía
    0.42
     gême
    0.42
     booze
    0.42
     llamar
    0.41
    רי
    0.41
     arkadaş
    0.41
     அழை
    0.41
     garantie
    0.40
    šenje
    0.40
    驾驶
    0.39
    Activations Density 0.002%

    No Known Activations