© 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. 98470
    Prev
    Next
    INDEX
    Explanations

    title: '`, Appellee

    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
    UNTIME
    -0.88
     mago
    -0.85
    PMID
    -0.83
    OMAS
    -0.83
     pecuni
    -0.83
     Lázaro
    -0.82
     Gnade
    -0.82
     ombro
    -0.80
    nią
    -0.80
    CHK
    -0.80
    POSITIVE LOGITS
     Plus
    0.79
    tit
    0.75
    quard
    0.75
    мора
    0.75
     espejo
    0.74
    ferrari
    0.74
     вересня
    0.74
     anillo
    0.73
    cipit
    0.73
    粉丝
    0.72
    Activations Density 0.016%

    No Known Activations