© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3353
    Prev
    Next
    INDEX
    Explanations

    weights, anime, center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     nombreux
    2.83
    年に
    2.52
    جع
    2.51
     ตา
    2.45
    釀
    2.44
     ماہ
    2.43
    上次
    2.42
    dated
    2.34
    널
    2.33
    龈
    2.29
    POSITIVE LOGITS
    7
    3.30
    rinsic
    3.06
    }°
    2.98
     entities
    2.87
    <unused2206>
    2.83
    6
    2.81
    8
    2.80
     competencies
    2.79
     combustion
    2.79
     NPD
    2.77
    Activations Density 0.900%

    No Known Activations