© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10682
    Prev
    Next
    INDEX
    Explanations

    vacuum chamber

    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_7_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
    მწიფ
    2.71
    ेक्षित
    2.64
    i
    2.58
    osito
    2.55
    পাত
    2.50
    न
    2.44
    ാലി
    2.35
    ourism
    2.34
    యా
    2.24
    igten
    2.22
    POSITIVE LOGITS
    는다
    2.89
    ும்
    2.83
    ات
    2.61
    ත්තේ
    2.61
     gezogen
    2.58
    댜
    2.49
     samoglas
    2.42
    합
    2.41
     verlie
    2.39
    près
    2.39
    Activations Density 0.004%

    No Known Activations