© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1337
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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_13_width_65k_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
     shedding
    1.04
     admittedly
    1.04
     fundamentally
    1.02
     (*
    1.02
     inherently
    1.01
     necessarily
    0.98
     (=
    0.96
     ({
    0.96
     impart
    0.96
     unavoid
    0.94
    POSITIVE LOGITS
    8
    2.13
    6
    2.11
    7
    2.05
    5
    2.00
    9
    1.99
    4
    1.94
    3
    1.84
    2
    1.63
    0
    1.59
    ８
    1.59
    Activations Density 1.287%

    No Known Activations