© 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. 6426
    Prev
    Next
    INDEX
    Explanations

    tsundere

    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
     Offences
    1.26
    វិញ
    1.12
     semn
    1.11
     Verständ
    1.11
     illet
    1.10
     definitiva
    1.10
    iritto
    1.10
    벗
    1.09
    瞬
    1.09
     comuns
    1.07
    POSITIVE LOGITS
     dinosaurs
    1.55
     pizzas
    1.52
     elves
    1.50
    лод
    1.49
    bered
    1.49
     pipeline
    1.48
    brenner
    1.46
    nels
    1.44
     subs
    1.44
     Advisors
    1.43
    Activations Density 0.000%

    No Known Activations