© 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. 44905
    Prev
    Next
    INDEX
    Explanations

    sorry, invalid, or refusal

    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
    Negative Logits
     accomplishments
    0.44
     insignia
    0.41
     management
    0.41
    :
    0.40
     сов
    0.40
     crick
    0.40
     во
    0.39
     circuit
    0.38
    (?)
    0.38
     aspect
    0.38
    POSITIVE LOGITS
    ющее
    0.47
    asie
    0.44
    粈
    0.44
     Invalid
    0.43
    দেব
    0.43
    ]}/
    0.43
     dãy
    0.42
     Preise
    0.41
    including
    0.41
     Including
    0.41
    Activations Density 0.011%

    No Known Activations