© 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-16K
    4. 5836
    Prev
    Next
    INDEX
    Explanations

    login credentials

    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_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
     Differences
    0.48
     '|
    0.47
     ReturnVal
    0.45
    𝔼
    0.45
    傳
    0.45
    ネイ
    0.43
     ,
    0.42
     Effectively
    0.41
     bmi
    0.41
     Gama
    0.41
    POSITIVE LOGITS
    ap
    0.57
    ca
    0.52
    ing
    0.51
    کم
    0.50
    fy
    0.49
    commodity
    0.47
    ä
    0.46
    ai
    0.45
    asida
    0.45
    un
    0.45
    Activations Density 0.048%

    No Known Activations