© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4735
    Prev
    Next
    INDEX
    Explanations

    ready to face it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    executor
    1.77
     جوا
    1.66
     Carb
    1.63
     fermentation
    1.63
    倒入
    1.61
    砾
    1.57
    Outcome
    1.51
     counterbalance
    1.51
    Multiline
    1.50
    listOf
    1.49
    POSITIVE LOGITS
    near
    1.11
     AGAIN
    1.09
     zob
    1.04
    again
    0.99
     escuela
    0.99
     proximate
    0.96
     again
    0.96
     書
    0.96
     clos
    0.95
     sighted
    0.94
    Activations Density 0.077%

    No Known Activations