© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1707
    Prev
    Next
    INDEX
    Explanations

    AI_naughtiness flag set to 100

    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
     速
    2.41
    ｖ
    2.40
    ouncement
    2.40
    จุ
    2.39
     amma
    2.36
    พี
    2.31
     Schae
    2.27
    organiser
    2.27
     (£
    2.26
     Vee
    2.21
    POSITIVE LOGITS
    7
    1.65
    rinsic
    1.50
    8
    1.48
    6
    1.43
    4
    1.22
    3
    1.21
    5
    1.19
    0
    1.06
     mesenchymal
    1.05
     }
    1.03
    Activations Density 1.140%

    No Known Activations