© 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. 34-GEMMASCOPE-RES-131K
    7. 93590
    Prev
    Next
    INDEX
    Explanations

    public zombies

    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_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
     phần
    -0.73
    агности
    -0.72
     reinforced
    -0.68
    illage
    -0.67
     protestas
    -0.67
     прогу
    -0.66
    FRC
    -0.66
     keindahan
    -0.65
    틸
    -0.65
    يمة
    -0.63
    POSITIVE LOGITS
    isierte
    0.70
     اسپ
    0.70
    pol
    0.66
     factory
    0.66
     pol
    0.66
    zten
    0.66
    akuan
    0.66
    CCC
    0.66
     Testing
    0.65
     Rakyat
    0.65
    Activations Density 0.042%

    No Known Activations