© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8013
    Prev
    Next
    INDEX
    Explanations

    fitting within boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
     credentials
    0.57
     hardships
    0.57
     possessions
    0.56
     dignity
    0.55
     credibility
    0.55
     guardianship
    0.55
    <unused2221>
    0.55
     adherence
    0.54
     thema
    0.54
     notions
    0.54
    POSITIVE LOGITS
    0.63
    ない
    0.58
     Вы
    0.54
    +
    0.51
    ของการ
    0.48
     بص
    0.48
    となります
    0.47
    として
    0.45
     vollständ
    0.45
     Accessed
    0.45
    Activations Density 0.109%

    No Known Activations