© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2394
    Prev
    Next
    INDEX
    Explanations

    cup upside down

    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
     soient
    1.54
    ](#
    1.53
    霹
    1.51
    疫
    1.42
    畿
    1.41
     pă
    1.40
     lived
    1.38
     eus
    1.31
     cualquiera
    1.28
     doves
    1.27
    POSITIVE LOGITS
    ff
    1.60
    chiha
    1.58
    гло
    1.57
    stanford
    1.57
    ید
    1.55
    rem
    1.52
    حد
    1.52
    ровень
    1.51
    ̯
    1.50
    сть
    1.49
    Activations Density 0.038%

    No Known Activations