© 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. 970
    Prev
    Next
    INDEX
    Explanations

    Quality Manager Responsibility List

    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
     Ueda
    1.57
    equival
    1.47
     Burbank
    1.45
    rinsic
    1.44
     escultura
    1.44
    4
    1.41
    candy
    1.40
     beli
    1.40
     Albanese
    1.38
    8
    1.37
    POSITIVE LOGITS
    Mo
    1.47
    mo
    1.36
    mi
    1.29
     Mo
    1.27
     Cro
    1.22
     sav
    1.06
     friend
    1.06
     speed
    1.05
     Vee
    1.05
    RECTION
    1.04
    Activations Density 0.011%

    No Known Activations