© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98570
    Prev
    Next
    INDEX
    Explanations

    Lovecraftian horror fiction

    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
    żył
    -0.77
    模样
    -0.71
     Philosop
    -0.70
    上学
    -0.70
    aną
    -0.69
    adget
    -0.69
     DICE
    -0.68
    édie
    -0.68
    눌
    -0.67
     Sachs
    -0.67
    POSITIVE LOGITS
    tilt
    0.70
     lidi
    0.69
     inferior
    0.66
     uyar
    0.66
    Unsupported
    0.65
    üssel
    0.65
     никаких
    0.65
    gemeester
    0.65
    чков
    0.65
    arien
    0.64
    Activations Density 0.035%

    No Known Activations