© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99258
    Prev
    Next
    INDEX
    Explanations

    perspective and viewpoint

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

    The neuron detects phrases that signal a particular viewpoint or perspective, such as “through the lens of…,” “looking from this perspective,” or “through … eyes.”

    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
     Scene
    -0.84
    LK
    -0.82
     scene
    -0.79
    boar
    -0.78
     Display
    -0.77
    assertIn
    -0.76
    UVWXYZ
    -0.75
    Sentence
    -0.75
    oning
    -0.74
     vmax
    -0.74
    POSITIVE LOGITS
     lens
    3.75
     lenses
    3.11
     prism
    2.52
    lens
    2.30
    Lens
    2.13
     Lens
    2.09
     Lenses
    1.97
    レンズ
    1.76
     eyes
    1.70
     filter
    1.68
    Activations Density 0.023%

    No Known Activations