© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32784
    Prev
    Next
    INDEX
    Explanations

    ability to neutralize

    np_acts-logits-general · gemini-2.5-flash-lite

    definitions or explanations that describe what a technical concept means or represents.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    θεν
    -1.16
     adegu
    -1.02
    ofte
    -0.99
     mulher
    -0.99
     persino
    -0.97
    Escrit
    -0.96
     HttpNotFound
    -0.94
    Cô
    -0.94
    optarg
    -0.93
     colleagues
    -0.92
    POSITIVE LOGITS
     during
    1.40
     when
    1.35
     that
    1.24
     whose
    1.15
    るのが
    1.12
    нули
    1.07
    的一种
    1.05
     after
    1.05
     or
    1.01
     before
    1.00
    Activations Density 0.043%

    No Known Activations