© 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. 6801
    Prev
    Next
    INDEX
    Explanations

    condition or outcome

    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
    omyel
    1.75
    oplasm
    1.62
    osis
    1.61
    oreg
    1.61
     reversal
    1.56
     Immer
    1.55
    ⎦
    1.55
    omyc
    1.54
     pulses
    1.50
    elapsed
    1.50
    POSITIVE LOGITS
    IgnoreCase
    1.30
    mē
    1.25
    ))/(
    1.24
    epat
    1.24
     kawa
    1.12
     erat
    1.09
     Routed
    1.09
    圏
    1.09
    Honor
    1.05
     posição
    1.05
    Activations Density 0.007%

    No Known Activations