© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1831
    Prev
    Next
    INDEX
    Explanations

    wonderful positive evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    atical
    1.23
    acycline
    1.21
     (
    1.20
    っかけ
    1.18
     कहलाता
    1.15
    ers
    1.14
     ganger
    1.13
    釀
    1.11
     historians
    1.11
    etil
    1.10
    POSITIVE LOGITS
    wonderful
    2.23
    素晴らしい
    2.15
     excelente
    2.09
     angene
    2.04
    Wow
    2.04
     wonderful
    2.01
     прекрасно
    1.99
     feel
    1.97
     meravigli
    1.96
     fascinating
    1.94
    Activations Density 0.471%

    No Known Activations