© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47516
    Prev
    Next
    INDEX
    Explanations

    importance and qualifier

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    umping
    0.44
     páginas
    0.44
    ágina
    0.44
     pagine
    0.41
     tí
    0.40
    ರಣ
    0.40
    itone
    0.40
    ucking
    0.39
    ipore
    0.39
    병
    0.38
    POSITIVE LOGITS
     Traditional
    0.44
     inequality
    0.44
     Economy
    0.40
     Reality
    0.40
    Julia
    0.40
     indis
    0.39
     substrate
    0.39
     traditional
    0.38
     inequalities
    0.37
     socialist
    0.37
    Activations Density 0.000%

    No Known Activations