© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6982
    Prev
    Next
    INDEX
    Explanations

    recommendation

    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
     verifiable
    0.90
    ondi
    0.90
     Strauss
    0.90
    +(-
    0.88
     торже
    0.87
    攤
    0.85
     Biografie
    0.85
    噸
    0.84
     Ereign
    0.84
    நில
    0.84
    POSITIVE LOGITS
     recommendation
    4.52
     recommend
    4.42
     recommendations
    4.31
    recommend
    4.19
     recommending
    4.08
     recommended
    4.07
     recomend
    4.04
     recommends
    3.97
     Recommendation
    3.97
    推荐
    3.93
    Activations Density 0.672%

    No Known Activations