© 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. 2088
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs and structures

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

    lists phrases following certain words

    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
     can
    0.63
     be
    0.57
     whatnot
    0.48
    鸫
    0.46
    মাণের
    0.43
    ्रेडिट
    0.43
     এজন্য
    0.43
    ید
    0.43
    in
    0.42
    ным
    0.42
    POSITIVE LOGITS
    ↵↵
    0.76
    0.70
    ０
    0.65
     ١
    0.58
    ，
    0.57
    mselves
    0.56
     라고
    0.55
     ,
    0.55
     ،
    0.53
    )
    0.53
    Activations Density 0.688%

    No Known Activations