© 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. 22-GEMMASCOPE-RES-131K
    7. 16085
    Prev
    Next
    INDEX
    Explanations

    times and events

    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_22/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
    ↵
    -1.38
    ύ
    -1.10
    Caller
    -0.96
     in
    -0.95
    heads
    -0.94
    ):
    -0.93
    рд
    -0.91
    heds
    -0.91
     berço
    -0.90
    hed
    -0.88
    POSITIVE LOGITS
    ﻻ
    1.18
     visitors
    1.09
    öra
    1.08
     interessi
    1.06
    ürm
    1.05
    
    1.05
    unduh
    1.05
    ⊨
    1.05
     membuka
    1.02
     aperto
    1.02
    Activations Density 0.015%

    No Known Activations