© 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. 84576
    Prev
    Next
    INDEX
    Explanations

    can say

    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
     انجام
    -1.02
    sedown
    -1.00
    initiate
    -0.96
     inaugura
    -0.96
     pirata
    -0.96
    敺
    -0.95
    Noten
    -0.93
     confuso
    -0.91
     levante
    -0.91
     repeats
    -0.90
    POSITIVE LOGITS
    hagic
    0.90
     väč
    0.84
     pierwszej
    0.84
     probablemente
    0.84
     pierwszym
    0.83
     pudieron
    0.82
     květ
    0.82
    =}
    0.81
    Aldrich
    0.81
     posiblemente
    0.81
    Activations Density 0.072%

    No Known Activations