© 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. 34-GEMMASCOPE-RES-131K
    7. 63618
    Prev
    Next
    INDEX
    Explanations

    IV or Ivy followed by other words

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

    The neuron detects occurrences of the uppercase bigram “IV” (as a standalone token or abbreviation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     freie
    -0.80
     interstitial
    -0.77
    ↵
    -0.72
     гли
    -0.70
    2
    -0.69
    Potential
    -0.69
    strain
    -0.68
    A
    -0.68
    Please
    -0.68
    现在的
    -0.68
    POSITIVE LOGITS
     Iv
    1.00
     league
    0.95
     League
    0.94
    illies
    0.84
    __(/*!
    0.83
    ینت
    0.82
    purposes
    0.82
    ッグ
    0.81
    orghe
    0.79
    asă
    0.78
    Activations Density 0.030%

    No Known Activations