© 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. 31399
    Prev
    Next
    INDEX
    Explanations

    emotional numbing and release

    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
     recommendations
    0.49
     aces
    0.46
     losses
    0.46
     accolades
    0.44
     factores
    0.43
     adhesions
    0.43
     Earrings
    0.43
    ༦
    0.43
    苇
    0.43
    ,",
    0.42
    POSITIVE LOGITS
    regener
    0.49
    ancienne
    0.44
    amending
    0.41
    ків
    0.41
    sensitive
    0.41
    ור
    0.41
    ਿੰ
    0.40
    í
    0.40
    ́ng
    0.40
    하고
    0.40
    Activations Density 0.016%

    No Known Activations