© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91769
    Prev
    Next
    INDEX
    Explanations

    contain or include

    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
     توانید
    -0.82
    CHES
    -0.81
    Mehr
    -0.80
    ItemBackground
    -0.79
     MÁS
    -0.79
     curto
    -0.79
     fuma
    -0.79
     genio
    -0.77
    extAlignment
    -0.77
     Grilled
    -0.76
    POSITIVE LOGITS
    디어
    0.84
    baba
    0.76
     seeker
    0.75
    IBase
    0.71
     Honour
    0.71
     Lleg
    0.70
     إ
    0.69
     Incluye
    0.69
     EDF
    0.68
     checker
    0.67
    Activations Density 0.001%

    No Known Activations