© 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. 4857
    Prev
    Next
    INDEX
    Explanations

    HTML `span` tags

    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
    koord
    1.51
    ଘ
    1.36
    áll
    1.35
    ătate
    1.34
     EMERG
    1.34
    ◝
    1.33
    LN
    1.30
    ūk
    1.28
    โรค
    1.27
    lež
    1.27
    POSITIVE LOGITS
     older
    2.23
     bars
    2.21
     store
    2.17
     stores
    2.13
     tor
    2.11
     hes
    2.10
     Edwards
    2.08
     longer
    2.08
    ette
    2.04
    izer
    2.03
    Activations Density 0.000%

    No Known Activations