© 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. 40-GEMMASCOPE-2-RES-65K
    7. 53410
    Prev
    Next
    INDEX
    Explanations

    passive voice and voice changes

    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_40_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
     Boundaries
    0.38
     Acceleration
    0.37
     hin
    0.36
     ఇంటి
    0.36
     Conjug
    0.36
     மட
    0.36
    rVert
    0.36
    }^{+}$.
    0.36
     Verb
    0.36
     Dian
    0.35
    POSITIVE LOGITS
     passive
    0.82
    passive
    0.77
    Passive
    0.71
     passively
    0.70
     Passive
    0.66
     existential
    0.61
     impersonal
    0.60
     constructions
    0.54
     passivation
    0.48
     inactive
    0.47
    Activations Density 0.130%

    No Known Activations