© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93121
    Prev
    Next
    INDEX
    Explanations

    specific points and locations

    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
    žky
    -0.88
    oncé
    -0.88
     moyens
    -0.84
    EREN
    -0.77
     chamado
    -0.77
     حالة
    -0.77
    ﻭ
    -0.76
    nome
    -0.75
    魃
    -0.75
    diocese
    -0.74
    POSITIVE LOGITS
     point
    4.09
     location
    3.88
     place
    3.69
     points
    3.55
     spot
    3.47
     places
    3.38
     locations
    3.28
     spots
    3.16
     position
    2.77
     место
    2.64
    Activations Density 0.188%

    No Known Activations