© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10610
    Prev
    Next
    INDEX
    Explanations

    Python module imports, constants, and attribute access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scenery
    1.45
     gives
    1.31
     exons
    1.30
     forbids
    1.29
    identité
    1.22
     chin
    1.20
     meadow
    1.20
    𒊹
    1.20
     fearless
    1.19
    泊
    1.19
    POSITIVE LOGITS
    ي
    1.70
    م
    1.50
    க
    1.42
    i
    1.28
    و
    1.25
    s
    1.22
    ύ
    1.19
    ی
    1.18
    eniz
    1.17
    ين
    1.17
    Activations Density 0.000%

    No Known Activations