© 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. 31-GEMMASCOPE-2-RES-65K
    7. 14800
    Prev
    Next
    INDEX
    Explanations

    originally intended, to prevent

    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_65k_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
    Entrepreneur
    0.46
    ט
    0.45
    Fe
    0.45
    Contributions
    0.44
    Alongside
    0.42
    Fif
    0.42
    ష
    0.42
    Ag
    0.42
    Administrative
    0.42
     উন্ন
    0.41
    POSITIVE LOGITS
    juang
    0.49
     pac
    0.46
    icast
    0.46
     încă
    0.46
    вра
    0.45
     col
    0.45
     extremo
    0.44
    ḿ
    0.44
     dot
    0.43
     hoon
    0.43
    Activations Density 0.033%

    No Known Activations