© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1409
    Prev
    Next
    INDEX
    Explanations

    (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esty
    0.59
    secretary
    0.57
    ลักษณ์
    0.54
    Commissioner
    0.54
     AMS
    0.53
    琦
    0.53
    ppery
    0.53
    elier
    0.53
     khăn
    0.52
    Secretary
    0.51
    POSITIVE LOGITS
    ノン
    0.70
     অবা
    0.59
    uski
    0.58
     indice
    0.58
    晩
    0.57
    onz
    0.56
     Yal
    0.56
    onn
    0.55
    ह्न
    0.55
     manuss
    0.55
    Activations Density 0.544%

    No Known Activations