© 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. 16033
    Prev
    Next
    INDEX
    Explanations

    newborn reaction, camera shake, item filters

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ButtonPressed
    -0.90
    cartoon
    -0.90
    lø
    -0.88
    enang
    -0.86
     například
    -0.81
    ໂ
    -0.81
     čia
    -0.81
    estroy
    -0.79
     stopping
    -0.78
    meow
    -0.78
    POSITIVE LOGITS
    ynku
    1.00
     않
    0.93
    "",
    
    0.92
    ΠΑ
    0.90
    $^{\
    0.87
    Formazione
    0.85
     =&
    0.85
    ffy
    0.85
     dokumen
    0.84
     findes
    0.83
    Activations Density 0.055%

    No Known Activations