© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2930
    Prev
    Next
    INDEX
    Explanations

    something followed by descriptors

    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
    Negative Logits
    ان
    4.92
    ма
    3.34
    ρα
    3.13
    ъ
    3.08
    ся
    2.98
    야
    2.91
    ून
    2.89
    च
    2.87
    𝗶
    2.86
     microtubules
    2.81
    POSITIVE LOGITS
    ا
    3.44
    sair
    3.28
    는
    3.04
    м
    2.97
     denominator
    2.95
     fluctu
    2.84
     unsur
    2.83
    sung
    2.82
    𝒅
    2.82
    siehe
    2.80
    Activations Density 0.285%

    No Known Activations