© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    predictive updates

    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
    ıl
    0.84
    疎
    0.74
    le
    0.69
    ă
    0.68
    らを
    0.66
    と考え
    0.64
    們
    0.64
     terv
    0.64
    them
    0.63
    们
    0.61
    POSITIVE LOGITS
     государ
    1.36
    Pose
    1.36
     государственных
    1.32
     Staats
    1.32
    federal
    1.27
    ικές
    1.27
     Breathe
    1.25
     Telecom
    1.24
     Aeros
    1.24
     كوساين
    1.23
    Activations Density 0.197%

    No Known Activations