© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5175
    Prev
    Next
    INDEX
    Explanations

    break down

    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
    Negative Logits
    fulness
    2.21
    際は
    1.98
    たたみ
    1.97
    ional
    1.93
    様子
    1.90
     pulleys
    1.89
     historians
    1.84
    佢
    1.84
    iddle
    1.84
    otransferase
    1.83
    POSITIVE LOGITS
    7
    4.09
    6
    3.88
    FFFFFF
    3.86
    8
    3.79
    9
    3.60
    леко
    3.56
    ffffff
    3.52
    VALUE
    3.46
     Санкт
    3.45
    3
    3.45
    Activations Density 0.045%

    No Known Activations