© 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. 20649
    Prev
    Next
    INDEX
    Explanations

    data security compliance

    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
    یک
    0.54
    대
    0.54
    더
    0.51
    lifts
    0.46
    탈
    0.46
     이름
    0.46
    دور
    0.46
    大道
    0.46
    اقات
    0.45
     베
    0.43
    POSITIVE LOGITS
     secundaria
    0.50
     secund
    0.47
     secondary
    0.46
     spontaneity
    0.46
    s
    0.44
     unavailability
    0.43
    året
    0.42
     unplanned
    0.42
    ᠶ
    0.42
     hairstyle
    0.42
    Activations Density 0.011%

    No Known Activations