© 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. 10924
    Prev
    Next
    INDEX
    Explanations

    hub for connections

    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
    た
    2.80
     জনের
    2.48
    loving
    2.35
    Francis
    2.21
    ㅁ
    2.20
    থ
    2.17
    issued
    2.15
    GA
    2.14
    བ་
    2.12
    당
    2.10
    POSITIVE LOGITS
    det
    3.15
    dn
    3.06
    bdb
    3.04
    nę
    3.01
    𝒖
    3.00
    uot
    3.00
    tól
    3.00
    imodal
    2.99
    ds
    2.94
    gid
    2.86
    Activations Density 0.010%

    No Known Activations