© 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. 3566
    Prev
    Next
    INDEX
    Explanations

    nested structures and pyramids

    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
    ेक्ट
    1.83
    boxplot
    1.50
    ומי
    1.49
    ချက်
    1.43
    ותר
    1.41
     UnitTest
    1.40
    ﮕ
    1.38
    esorios
    1.35
    บบ
    1.33
     Qualität
    1.33
    POSITIVE LOGITS
    lands
    1.42
     into
    1.37
    len
    1.36
    land
    1.32
    ly
    1.23
    lo
    1.23
     vào
    1.21
     asleep
    1.20
     r
    1.17
    hookrightarrow
    1.13
    Activations Density 0.069%

    No Known Activations