© 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. 6590
    Prev
    Next
    INDEX
    Explanations

    Sustainability Ordering

    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
    kurs
    1.69
    acetamol
    1.65
    svelte
    1.58
     dgn
    1.56
    窘
    1.55
    🦷
    1.55
    exch
    1.53
    ÉR
    1.50
     Negoti
    1.50
    𝟐
    1.50
    POSITIVE LOGITS
    alloway
    1.25
     tracks
    1.20
     admirers
    1.18
     coverage
    1.14
     payback
    1.10
     involvement
    1.10
     pledges
    1.10
    lover
    1.09
     followers
    1.08
     intends
    1.08
    Activations Density 0.009%

    No Known Activations