© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    methods and trajectories

    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
    本当に
    1.69
     Hãy
    1.67
     informations
    1.62
     SiO
    1.62
    ѣ
    1.60
     الغير
    1.57
     🙏
    1.56
     BSc
    1.56
    令和
    1.56
     capire
    1.54
    POSITIVE LOGITS
     concomit
    1.32
    嬗
    1.26
     incipient
    1.25
     doubtless
    1.23
     undercut
    1.22
     jost
    1.21
    launcher
    1.19
     chaf
    1.18
     Wnd
    1.18
     conspicuously
    1.18
    Activations Density 0.618%

    No Known Activations