© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 57122
    Prev
    Next
    INDEX
    Explanations

    describing conditional or occasional actions

    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
     monotonicity
    0.43
    𒅆
    0.42
     회사
    0.41
    DFS
    0.40
     двох
    0.39
    瘦
    0.39
    ﺜ
    0.39
    TextBlock
    0.38
     cale
    0.38
     Igre
    0.38
    POSITIVE LOGITS
     aswell
    0.51
     aims
    0.49
    goals
    0.48
     goals
    0.47
    asını
    0.45
    overrightarrow
    0.45
    𝘯
    0.44
     Ziele
    0.43
     gonf
    0.43
    '\
    0.43
    Activations Density 0.005%

    No Known Activations