© 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. 490
    Prev
    Next
    INDEX
    Explanations

    the impossibility of

    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
    yon
    0.99
    ron
    0.94
    ober
    0.92
    isz
    0.91
    Y
    0.90
    ani
    0.90
    jun
    0.89
    ap
    0.87
    -
    0.87
     aż
    0.85
    POSITIVE LOGITS
     usual
    1.58
    以往
    1.36
    usual
    1.29
    预期
    1.21
     envisaged
    1.20
    传统的
    1.14
     Usual
    1.14
     anticipated
    1.13
     normale
    1.13
    expected
    1.08
    Activations Density 1.115%

    No Known Activations