© 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. 10558
    Prev
    Next
    INDEX
    Explanations

    building, defining, estimating, describing

    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
    бто
    0.91
     postérieures
    0.91
    нибудь
    0.88
    деся
    0.88
    Brightness
    0.86
    ܵ
    0.86
     competencias
    0.86
    כן
    0.85
     тобто
    0.85
    Object
    0.85
    POSITIVE LOGITS
    abl
    0.75
    rite
    0.71
    adel
    0.68
    ue
    0.66
    resher
    0.65
    enet
    0.64
    ani
    0.63
    iles
    0.63
    u
    0.63
    iple
    0.62
    Activations Density 0.000%

    No Known Activations