© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2443
    Prev
    Next
    INDEX
    Explanations

    sum when

    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_22_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
    ش
    1.08
     bersifat
    1.00
    falls
    0.96
     pełni
    0.94
    ிற
    0.91
    我认为
    0.91
    èche
    0.90
    ουμε
    0.89
    솜
    0.88
    ੍ਹ
    0.88
    POSITIVE LOGITS
    imposed
    1.44
    ZUKI
    1.37
     imposed
    1.34
    ptuous
    1.34
    denly
    1.32
    ᵢ
    1.27
    ल्तान
    1.27
    ម្បី
    1.25
    臾
    1.23
    ņa
    1.21
    Activations Density 0.466%

    No Known Activations