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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5055
    Prev
    Next
    INDEX
    Explanations

    exploring relationships and data

    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
    red
    0.44
     angesch
    0.44
    Keg
    0.43
    rän
    0.42
    เนื้อ
    0.41
    okolade
    0.41
    鸚
    0.41
     Goy
    0.40
     karit
    0.40
     اجر
    0.40
    POSITIVE LOGITS
     सतह
    0.49
     Enseñ
    0.47
     Гер
    0.43
    a
    0.43
     przestr
    0.43
     defined
    0.43
     definido
    0.42
    AME
    0.42
     வரை
    0.42
     कृ
    0.41
    Activations Density 0.015%

    No Known Activations