© 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. 5925
    Prev
    Next
    INDEX
    Explanations

    what's been

    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
    l
    4.45
    ка
    4.23
    v
    3.59
    r
    3.56
    or
    3.52
    x
    3.50
    w
    3.42
    ки
    3.36
    y
    3.35
    t
    3.32
    POSITIVE LOGITS
     been
    4.52
     Been
    3.65
    been
    3.26
     gotta
    3.20
     BEEN
    3.18
     sido
    2.66
    queous
    2.55
     got
    2.49
    icularly
    2.44
     varit
    2.34
    Activations Density 0.647%

    No Known Activations