© 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-262K
    7. 18658
    Prev
    Next
    INDEX
    Explanations

    concept and idea definitions

    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_262k_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
    的
    0.43
     school
    0.42
     graded
    0.42
     considering
    0.41
     subscription
    0.41
     amputation
    0.40
     Considering
    0.39
     meta
    0.39
     W
    0.39
     short
    0.39
    POSITIVE LOGITS
    సాగ
    0.51
     遊ん
    0.48
     CtApp
    0.47
    ódigo
    0.44
     書い
    0.44
     kritis
    0.44
     Miłos
    0.44
    uchtigkeit
    0.43
     starke
    0.43
    tAux
    0.43
    Activations Density 0.000%

    No Known Activations