© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2212
    Prev
    Next
    INDEX
    Explanations

    names followed by titles or descriptions

    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_16k_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
    ية
    1.31
    𝑈
    1.12
     Plateau
    1.10
    ▥
    1.08
    État
    1.07
    
    1.04
    StudentID
    1.03
    Во
    1.03
    écriture
    1.02
    Ме
    1.02
    POSITIVE LOGITS
     other
    1.22
     fucking
    1.20
    y
    1.18
     ble
    1.17
     freaking
    1.16
     inactiv
    1.12
     utter
    1.11
     dissipated
    1.09
    i
    1.09
     regrett
    1.08
    Activations Density 0.069%

    No Known Activations