© 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-65K
    7. 62839
    Prev
    Next
    INDEX
    Explanations

    specific verbs followed by complements

    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_65k_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
     दर
    0.40
    ").
    0.40
     Monroe
    0.39
    ').
    0.38
    ங்கள்
    0.37
    ahan
    0.37
    人
    0.37
    })
    0.36
    ,
    0.36
    ik
    0.36
    POSITIVE LOGITS
     aisles
    0.58
     fertilisers
    0.57
     fertilizers
    0.56
     pulau
    0.54
     treatments
    0.53
     fertilization
    0.52
     shoots
    0.52
     strikeouts
    0.52
     islands
    0.51
     Фургал
    0.51
    Activations Density 0.002%

    No Known Activations