© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9520
    Prev
    Next
    INDEX
    Explanations

    mystery and detective work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     الجيش
    0.58
     Transmission
    0.55
    Normalize
    0.55
     Crush
    0.54
     Warrior
    0.54
     normalizing
    0.54
     యుద్ధ
    0.54
     normalization
    0.53
     Transformer
    0.53
    엄
    0.52
    POSITIVE LOGITS
     detective
    1.94
     murder
    1.93
     crime
    1.83
     detectives
    1.83
    Murder
    1.72
     Detective
    1.71
     murders
    1.70
    Detective
    1.67
     Murder
    1.63
    murder
    1.62
    Activations Density 0.253%

    No Known Activations