© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 30130
    Prev
    Next
    INDEX
    Explanations

    but introduces contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
     not
    0.80
     Without
    0.66
    not
    0.64
    Without
    0.60
     (
    0.58
     without
    0.58
     zonder
    0.57
     cannot
    0.56
    {.
    0.55
     (--
    0.53
    POSITIVE LOGITS
     élus
    0.66
    time
    0.63
     duelo
    0.61
    ஜ்மஹால்
    0.60
     montañas
    0.60
     škola
    0.60
     सीएच
    0.58
     CED
    0.58
     doraemon
    0.58
    বৃত্ত
    0.58
    Activations Density 0.087%

    No Known Activations