© 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. 326
    Prev
    Next
    INDEX
    Explanations

    verbs following "to"

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

    infinitive verb phrases

    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
    ه
    0.24
    を満
    0.23
     Wanneer
    0.22
    Կ
    0.21
    または
    0.21
    을
    0.21
    NOWLEDGE
    0.21
    𝘐
    0.20
     नामक
    0.20
    ().
    0.20
    POSITIVE LOGITS
     do
    0.23
     see
    0.23
     be
    0.23
     have
    0.22
     encourage
    0.21
     hear
    0.21
     know
    0.21
    ady
    0.20
     put
    0.20
     convince
    0.20
    Activations Density 1.118%

    No Known Activations