© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10833
    Prev
    Next
    INDEX
    Explanations

    stumble upon

    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
     weniger
    1.07
    ार्थी
    0.99
    :.
    0.96
    :-
    0.92
     করলেও
    0.88
    立
    0.88
    -:
    0.88
     though
    0.87
    :/
    0.86
     static
    0.86
    POSITIVE LOGITS
     ?)
    1.27
     )
    1.24
     ...)
    1.18
     ){
    1.12
    ..)
    1.09
    ?)
    1.04
     })
    1.04
     $)$
    1.01
    ...)
    1.01
     ),
    1.00
    Activations Density 0.001%

    No Known Activations