© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10744
    Prev
    Next
    INDEX
    Explanations

    coffee, ATL, PTS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ead
    3.17
    eh
    2.68
    ة
    2.49
    eis
    2.45
    ez
    2.41
    ech
    2.41
    ed
    2.40
    Personensuche
    2.39
    gaz
    2.38
    此之外
    2.37
    POSITIVE LOGITS
    <0xBE>
    2.53
    чего
    2.34
    rombin
    2.28
     bang
    2.25
    ्य
    2.25
    涓
    2.25
    asinya
    2.24
    ի
    2.23
     cool
    2.22
    getTo
    2.22
    Activations Density 0.014%

    No Known Activations