© 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. 2317
    Prev
    Next
    INDEX
    Explanations

    categorized lists and items

    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
    ↵
    1.57
    ↵↵
    1.44
    ernation
    1.19
    imeters
    1.14
    inations
    1.08
     Finally
    1.07
    ↵↵↵
    1.07
    requency
    1.06
     Divided
    1.06
    alarında
    1.04
    POSITIVE LOGITS
    <h1>
    1.53
    <h4>
    1.33
    <h5>
    1.29
     воспроиз
    1.24
    Load
    1.23
    】.
    1.23
    引用
    1.23
    Ки
    1.22
     невро
    1.22
    질
    1.22
    Activations Density 0.051%

    No Known Activations