© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9417
    Prev
    Next
    INDEX
    Explanations

    coordinate systems

    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
    E
    2.45
    D
    2.40
    T
    2.26
    M
    2.23
    A
    2.23
    TIA
    2.09
     }$
    2.08
    L
    2.06
    et
    2.03
    I
    2.02
    POSITIVE LOGITS
    ्स
    2.59
    এর
    2.23
    consuming
    2.22
    shaped
    2.22
     teria
    2.00
     Zust
    1.96
    ِي
    1.95
    inspired
    1.91
     pengg
    1.90
    absorbing
    1.89
    Activations Density 0.093%

    No Known Activations