© 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. 1620
    Prev
    Next
    INDEX
    Explanations

    output examples

    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
     cinematography
    1.64
    ️⃣
    1.61
    TikTok
    1.56
     Tiktok
    1.54
    🤌
    1.53
     Selfie
    1.52
     TikTok
    1.51
     tiktok
    1.49
    tiktok
    1.47
    👀
    1.46
    POSITIVE LOGITS
     mailing
    1.75
    หาย
    1.65
     discussão
    1.62
    委员会
    1.58
    msg
    1.57
     REPLY
    1.57
    unsubscribe
    1.56
     обсу
    1.56
     Mailing
    1.55
     üy
    1.55
    Activations Density 0.238%

    No Known Activations