© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12672
    Prev
    Next
    INDEX
    Explanations

    ETF Trust

    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
    ل
    2.94
    瘩
    2.79
    radle
    2.77
    ثير
    2.73
    nown
    2.72
    লস
    2.67
    ع
    2.63
    لون
    2.61
    ypress
    2.60
    ípio
    2.59
    POSITIVE LOGITS
    ef
    2.56
     mcm
    2.53
    efi
    2.51
    eh
    2.47
    ech
    2.35
    QUIN
    2.29
    >
    2.27
    OGEN
    2.27
    PR
    2.25
    TE
    2.25
    Activations Density 0.001%

    No Known Activations