© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112453
    Prev
    Next
    INDEX
    Explanations

    OAuth 2.0 or Erectile dysfunction

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

    the token "Ere" at the beginning of the word "Erectile" or variations of "OAuth" in technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    -3.28
    i
    -3.09
    d
    -3.03
     has
    -2.94
    ſſel
    -2.64
    鋱
    -2.55
    せよ
    -2.50
     doesn
    -2.47
    ⭓
    -2.47
    s
    -2.45
    POSITIVE LOGITS
    1
    2.94
     erstes
    2.67
     larges
    2.64
    雰囲
    2.56
    更加
    2.56
     byproduct
    2.55
    兒子
    2.53
     goof
    2.53
     Coupled
    2.44
     Including
    2.42
    Activations Density 0.009%

    No Known Activations