© 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. 7422
    Prev
    Next
    INDEX
    Explanations

    while not qualified

    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
     además
    1.45
     nämlich
    1.44
     instead
    1.42
    instead
    1.41
     malah
    1.34
     ovvero
    1.26
    even
    1.24
    +:
    1.22
    :
    1.21
     außerdem
    1.19
    POSITIVE LOGITS
     nominally
    1.86
     initially
    1.81
     technically
    1.66
     admittedly
    1.65
     superficially
    1.61
     outwardly
    1.60
     initial
    1.51
     ostensibly
    1.49
     undoubtedly
    1.42
    initial
    1.42
    Activations Density 0.370%

    No Known Activations