© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16652
    Prev
    Next
    INDEX
    Explanations

    recognizing specific entities and concepts

    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
     x
    0.46
    </h3>
    0.43
     خ
    0.43
     On
    0.41
     \\
    0.40
    ção
    0.39
     tarix
    0.38
    상
    0.37
    kh
    0.37
     الخ
    0.37
    POSITIVE LOGITS
    owaniu
    0.36
    ،
    0.36
    ിലാണ്
    0.36
    ከላከ
    0.36
     இருப்பதால்
    0.35
     newbies
    0.35
    ®,
    0.35
     cần
    0.34
     tweeter
    0.34
    ्यूड
    0.34
    Activations Density 0.259%

    No Known Activations