© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 7644
    Prev
    Next
    INDEX
    Explanations

    single letters or numbers followed by context

    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
    M
    1.74
    D
    1.68
    L
    1.55
    T
    1.53
    in
    1.53
    S
    1.53
    A
    1.44
    R
    1.43
    C
    1.41
    DSP
    1.39
    POSITIVE LOGITS
    án
    1.27
    ்
    1.18
     canción
    1.17
     socializing
    1.16
    ING
    1.16
     unem
    1.11
     значит
    1.09
    İ
    1.09
     soggetti
    1.08
    orie
    1.08
    Activations Density 0.181%

    No Known Activations