© 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. 2775
    Prev
    Next
    INDEX
    Explanations

    English proficiency and speaking

    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
    ρια
    2.85
    intero
    2.55
    nament
    2.52
    तावनी
    2.51
    ilege
    2.41
    ग्रस्त
    2.38
    互联网档案馆
    2.37
    cribes
    2.36
    할
    2.34
    alias
    2.33
    POSITIVE LOGITS
    я
    4.69
    speaking
    3.94
    Speaking
    3.35
    ु
    3.16
     Speaking
    3.01
    ী
    2.93
     سلس
    2.85
     spoken
    2.81
    वार
    2.80
    𝗄
    2.78
    Activations Density 0.235%

    No Known Activations