© 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. 46195
    Prev
    Next
    INDEX
    Explanations

    place name

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

    Generally, likely, quickly, what

    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
     heretofore
    0.43
     paranoid
    0.42
     occupants
    0.41
     gunshot
    0.41
    Managed
    0.40
    %>%
    0.40
     unanswered
    0.39
    Finland
    0.39
     midfielders
    0.39
     stateless
    0.39
    POSITIVE LOGITS
     แต
    0.50
    腴
    0.47
    價格
    0.46
    書籍
    0.46
     وإ
    0.46
    ôn
    0.45
    講的是
    0.45
     وتق
    0.45
     বিদ্যা
    0.45
     على
    0.45
    Activations Density 0.000%

    No Known Activations