© 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. 22-GEMMASCOPE-RES-131K
    7. 72127
    Prev
    Next
    INDEX
    Explanations

    I have

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

    The neuron detects personal-biography style statements describing the author’s own identity or experiences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ďal
    -0.98
     všetky
    -0.97
     simplemente
    -0.93
     niekoľ
    -0.90
     natomiast
    -0.86
     ľah
    -0.85
     niektor
    -0.85
    contentInset
    -0.84
    noticias
    -0.84
     niečo
    -0.83
    POSITIVE LOGITS
    btw
    1.08
     eser
    1.03
     هاي
    1.02
     btw
    1.02
     memang
    1.00
     ugy
    0.97
    BTW
    0.94
     optik
    0.91
     cowok
    0.91
    mittedly
    0.89
    Activations Density 0.045%

    No Known Activations