© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 81466
    Prev
    Next
    INDEX
    Explanations

    quotation marks and specific words

    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_31_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
    бно
    0.47
     heatmap
    0.46
     در
    0.46
     கொஞ்சம்
    0.45
    ميل
    0.43
    𝓇
    0.43
    бору
    0.43
     demean
    0.42
    cooled
    0.42
    bentuk
    0.42
    POSITIVE LOGITS
    的的
    0.57
    ного
    0.48
     puisse
    0.47
     “”
    0.44
    Ahh
    0.41
     reorgan
    0.41
    ong
    0.40
    anet
    0.40
     a
    0.39
    opal
    0.39
    Activations Density 0.038%

    No Known Activations