© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53733
    Prev
    Next
    INDEX
    Explanations

    environment variables and code syntax

    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_31_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
    イン
    0.44
    ਬਰ
    0.44
     プラ
    0.43
     दिखा
    0.43
     leggere
    0.42
    ｉ
    0.42
     ジ
    0.42
    ารา
    0.42
    İN
    0.41
     відді
    0.41
    POSITIVE LOGITS
     nebo
    0.45
     ||=
    0.44
    hasOwnProperty
    0.41
     قوان
    0.40
     eller
    0.40
     treasures
    0.40
     or
    0.39
     ☐
    0.39
     ||
    0.39
    房地产
    0.39
    Activations Density 0.039%

    No Known Activations