© 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. 2177
    Prev
    Next
    INDEX
    Explanations

    each followed by subsequent word

    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
    т
    3.29
     relev
    2.87
    าค
    2.80
    না
    2.70
     quem
    2.51
    дения
    2.51
    ں
    2.51
     leche
    2.46
     ayudas
    2.45
     agua
    2.41
    POSITIVE LOGITS
    ل
    3.28
    ن
    3.07
    
    3.03
     successive
    3.01
    Ŷ
    2.67
    el
    2.63
    siniz
    2.62
    
    2.55
    अ
    2.53
     diathermy
    2.50
    Activations Density 0.078%

    No Known Activations