© 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. 11591
    Prev
    Next
    INDEX
    Explanations

    clip training

    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
    设
    2.40
     dia
    2.14
    瘩
    2.10
    alay
    2.03
    డం
    1.97
    dü
    1.94
     लिखी
    1.94
    Dia
    1.93
    itemconfig
    1.93
    டியாக
    1.93
    POSITIVE LOGITS
    傈
    2.11
     hikers
    2.09
     pleasantly
    2.08
     신
    2.07
    噛
    2.06
     yield
    2.05
     preserve
    2.05
     significantly
    2.04
    payer
    2.03
     heft
    2.03
    Activations Density 0.000%

    No Known Activations