© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6955
    Prev
    Next
    INDEX
    Explanations

    unix directory paths

    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_22_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
    attuale
    0.86
    なくても
    0.83
     upper
    0.83
    unjukan
    0.83
    izare
    0.81
    женной
    0.81
    寝
    0.80
    unding
    0.79
    체
    0.79
    probs
    0.78
    POSITIVE LOGITS
    usr
    1.35
    mnt
    1.26
    var
    1.23
    Users
    1.14
    Volumes
    1.07
    opt
    1.07
    home
    1.04
    proc
    1.03
    bolic
    1.00
     ∈
    1.00
    Activations Density 0.019%

    No Known Activations