© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25648
    Prev
    Next
    INDEX
    Explanations

    conditional phrases

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

    The neuron flags sensational or shock-value words—dramatic, violent, or emotionally charged tokens (e.g. “story,” “hell,” “bullets,” “shocking,” etc.).

    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
    /*
    -1.04
    I
    -1.00
     работу
    -0.97
    HASAN
    -0.96
    BOOST
    -0.95
     heretics
    -0.95
    /
    -0.94
    It
    -0.94
    als
    -0.94
    \'
    -0.94
    POSITIVE LOGITS
     späteren
    1.01
     tématu
    1.01
    atán
    0.96
     while
    0.95
     efekt
    0.94
    埂
    0.93
     disciplinas
    0.92
     koš
    0.91
    Horrible
    0.91
     womit
    0.90
    Activations Density 0.080%

    No Known Activations