© 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. 15-GEMMASCOPE-2-RES-16K
    7. 573
    Prev
    Next
    INDEX
    Explanations

    action or decision contexts

    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
     kategorie
    1.23
    Attributes
    1.14
    一定的
    1.13
     komponent
    1.08
    :/
    1.08
    frast
    1.07
    EMY
    1.07
    醍
    1.04
    apagos
    1.03
    Resources
    1.02
    POSITIVE LOGITS
     announcement
    2.20
     decision
    1.90
     proposal
    1.86
     incident
    1.84
     memo
    1.83
     lawsuit
    1.80
     request
    1.78
     manoeuvre
    1.74
     requête
    1.74
     move
    1.71
    Activations Density 4.768%

    No Known Activations