© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2131
    Prev
    Next
    INDEX
    Explanations

    how to use 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
     brainstorm
    1.63
    描写
    1.60
     brainstorming
    1.59
    したいと思います
    1.54
    dump
    1.49
     ị
    1.49
     rework
    1.48
     electroneg
    1.48
    倾
    1.46
     боли
    1.44
    POSITIVE LOGITS
    Tickets
    1.54
     admittance
    1.50
     admis
    1.42
     tickets
    1.40
     ticket
    1.38
     admission
    1.38
    ingresso
    1.37
     ingresso
    1.32
     Tickets
    1.32
     Admission
    1.31
    Activations Density 0.505%

    No Known Activations