© 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. 11256
    Prev
    Next
    INDEX
    Explanations

    bash scripts

    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
    responseTime
    2.70
    isinde
    2.59
     QTreeWidgetItem
    2.57
    க்கொண்ட
    2.51
    टाइ
    2.51
    𝙧
    2.48
    Printf
    2.48
     pursuing
    2.47
    getic
    2.44
    𝗬
    2.40
    POSITIVE LOGITS
    sville
    2.41
    ly
    2.13
     fred
    2.12
     disso
    2.08
    תי
    2.07
    दायक
    2.06
    a
    2.03
    یشہ
    2.03
     இருப்ப
    1.98
    le
    1.98
    Activations Density 0.011%

    No Known Activations