© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6137
    Prev
    Next
    INDEX
    Explanations

    technical explanations and code

    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_12_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
     zhī
    1.36
    bosch
    1.28
    iann
    1.27
    ファー
    1.25
    |}\
    1.23
     fēng
    1.21
     insur
    1.20
     Faso
    1.20
     Sylvain
    1.19
    adur
    1.19
    POSITIVE LOGITS
     JK
    1.25
     BB
    1.19
    亚马
    1.18
     MO
    1.17
     Barak
    1.16
    クレ
    1.16
    燒
    1.15
     popped
    1.14
    灼
    1.13
     pops
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.