© 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. 31-GEMMASCOPE-2-RES-65K
    7. 44998
    Prev
    Next
    INDEX
    Explanations

    ladder safety

    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
     вообще
    0.45
     abs
    0.42
     guns
    0.42
     tattoos
    0.41
     उन्‍हें
    0.41
     slush
    0.41
    =["
    0.41
     killings
    0.41
     arrived
    0.40
     Neend
    0.40
    POSITIVE LOGITS
    सत
    0.40
    ਹੀ
    0.38
     canaliculato
    0.35
    安
    0.35
    valuation
    0.34
     MARC
    0.34
    回事
    0.34
    rchen
    0.34
     السياسي
    0.34
    CES
    0.33
    Activations Density 0.001%

    No Known Activations