© 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. 128257
    Prev
    Next
    INDEX
    Explanations

    invincible, indestructible, unstoppable

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

    The neuron activates on adjectives and labels that convey extreme invulnerability or unbreakability (e.g. “invincible,” “indestructible,” “bulletproof”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     `
    -1.91
     =
    -1.90
    </em>
    -1.85
     ´
    -1.80
     \"
    -1.79
    『
    -1.79
    ꦫ
    -1.70
     середине
    -1.64
    ?
    -1.64
     '
    -1.62
    POSITIVE LOGITS
     Like
    1.94
     However
    1.87
     was
    1.81
     Unfortunately
    1.77
    地在
    1.71
     jornalista
    1.70
    rangian
    1.69
     мем
    1.69
    rália
    1.67
     personalizar
    1.66
    Activations Density 0.013%

    No Known Activations