© 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. 10823
    Prev
    Next
    INDEX
    Explanations

    api keys

    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
    town
    1.04
    leading
    1.01
    ٻ
    0.98
    sset
    0.98
     continuum
    0.97
     Other
    0.95
     संतु
    0.94
    boosting
    0.94
     समझने
    0.94
     encompassing
    0.94
    POSITIVE LOGITS
    에는
    1.41
    ごろ
    1.40
    以來
    1.34
    以来
    1.32
    쯤
    1.31
    말
    1.30
    以後
    1.24
    下旬
    1.22
     itibaren
    1.20
    에도
    1.19
    Activations Density 0.012%

    No Known Activations