© 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. 73392
    Prev
    Next
    INDEX
    Explanations

    code, addresses, or license blocks

    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
    ऑ
    -0.85
    JUST
    -0.74
    ໄ
    -0.73
    otor
    -0.71
     escolher
    -0.69
     pinching
    -0.67
    MOB
    -0.67
    тья
    -0.67
     sangu
    -0.66
    geordnete
    -0.65
    POSITIVE LOGITS
     carga
    0.76
     probation
    0.69
     estas
    0.68
     répondit
    0.67
     bestehen
    0.66
     馬
    0.66
     progresses
    0.66
    neaux
    0.65
     survive
    0.65
     perhatian
    0.65
    Activations Density 0.060%

    No Known Activations