© 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. 17-GEMMASCOPE-2-RES-16K
    7. 6390
    Prev
    Next
    INDEX
    Explanations

    noun preceding specific term

    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_17_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
    𝘦
    1.48
    𝘰
    1.41
    𝘻
    1.38
    𝘨
    1.37
    𝘮
    1.36
    𝘧
    1.35
    𝘬
    1.33
     spying
    1.33
    𝘸
    1.33
    𝘩
    1.31
    POSITIVE LOGITS
    c
    1.22
    র
    1.17
    べき
    1.15
    t
    1.13
    競馬
    1.13
    ным
    1.09
    nen
    1.09
    ture
    1.09
     cilt
    1.07
    야
    1.02
    Activations Density 0.001%

    No Known Activations