© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 3826
    Prev
    Next
    INDEX
    Explanations

    initial descriptive phrases

    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
    📠
    1.37
    <unused2184>
    1.36
     និង
    1.33
    <unused2148>
    1.30
     및
    1.28
    📪
    1.27
    🕣
    1.26
     unveils
    1.25
    <unused2123>
    1.24
     راجسټ
    1.23
    POSITIVE LOGITS
    An
    1.11
     the
    1.07
    A
    1.05
     other
    1.04
    The
    0.98
     a
    0.97
    To
    0.93
    In
    0.92
    Стро
    0.91
    Or
    0.89
    Activations Density 0.305%

    No Known Activations