© 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. 59305
    Prev
    Next
    INDEX
    Explanations

    subjects followed by verbs

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

    pronoun or name followed by verb

    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
     πραγμα
    0.39
    擇
    0.38
     freezer
    0.38
    部屋
    0.38
     séquence
    0.38
    勻
    0.38
    失效
    0.37
     اح
    0.37
     Vacuum
    0.37
    机器
    0.36
    POSITIVE LOGITS
     decirlo
    0.53
     referring
    0.52
     এটাও
    0.52
     reasoning
    0.50
     emphasized
    0.50
     далее
    0.50
     further
    0.48
     কথাটা
    0.48
     emphasize
    0.48
     zároveň
    0.48
    Activations Density 0.077%

    No Known Activations