© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28664
    Prev
    Next
    INDEX
    Explanations

    harder to follow

    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
     impactful
    0.49
     fantastical
    0.44
     unsol
    0.41
    soaked
    0.41
     tinggal
    0.41
     unapolog
    0.40
    겠습니다
    0.40
    혁
    0.40
     healthcare
    0.40
     dystopian
    0.40
    POSITIVE LOGITS
    以内
    0.43
     lecz
    0.43
    Electron
    0.41
    偽
    0.41
     نسخه
    0.40
    tronic
    0.40
    ACE
    0.37
    Automatic
    0.37
     زیرا
    0.37
    Visual
    0.36
    Activations Density 0.007%

    No Known Activations