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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1978
    Prev
    Next
    INDEX
    Explanations

    stellar and planetary formation

    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_40_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
     уены
    0.43
    运算符
    0.42
    情报
    0.41
    荸
    0.40
    专业
    0.40
     жүктөп
    0.39
    无限
    0.38
    俄罗斯
    0.38
    ╽
    0.38
    宪
    0.38
    POSITIVE LOGITS
     progenitors
    0.64
     progenitor
    0.60
     accretion
    0.52
     thermally
    0.50
     luminosity
    0.49
     quiescent
    0.49
     gas
    0.49
     protop
    0.49
     thermal
    0.47
     stellar
    0.47
    Activations Density 0.048%

    No Known Activations