© 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. 10796
    Prev
    Next
    INDEX
    Explanations

    rain falling grey

    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
    ExpNow
    3.12
    鴦
    3.08
    <unused2172>
    2.95
    炽
    2.92
     subtlet
    2.89
    <unused608>
    2.85
    <unused1625>
    2.84
    inase
    2.83
     divaricatis
    2.82
    utches
    2.80
    POSITIVE LOGITS
    o
    2.28
    eur
    2.26
    @",
    2.14
    eurs
    2.12
    ς
    2.10
    ة
    2.09
    ez
    2.03
    eel
    2.02
    "
    2.01
    ed
    2.00
    Activations Density 0.006%

    No Known Activations