© 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. 5134
    Prev
    Next
    INDEX
    Explanations

    word completions or phrase continuations

    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
     proclaims
    1.01
    📠
    0.92
    <unused2184>
    0.89
     condemns
    0.88
    🚭
    0.88
     racconta
    0.87
     និង
    0.85
     blames
    0.84
    ystycz
    0.84
    📪
    0.83
    POSITIVE LOGITS
    An
    0.62
    D
    0.60
    To
    0.60
    Compound
    0.59
     other
    0.58
    Tensor
    0.55
    Computational
    0.54
     the
    0.54
    Gaussian
    0.54
    Fourier
    0.54
    Activations Density 0.286%

    No Known Activations