© 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. 3398
    Prev
    Next
    INDEX
    Explanations

    helps to simplify, stabilize, or 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
    \
    0.44
    이는
    0.44
     an
    0.43
    4
    0.42
    이가
    0.40
     antigo
    0.40
    或
    0.40
     وهذه
    0.39
    أ
    0.38
    㕩
    0.38
    POSITIVE LOGITS
     tremendously
    0.52
     to
    0.49
     diminue
    0.49
     simplifies
    0.47
     stabilize
    0.47
     prevents
    0.46
     réduire
    0.46
     overcome
    0.45
     jeopard
    0.45
     fordi
    0.45
    Activations Density 0.051%

    No Known Activations