© 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. 57982
    Prev
    Next
    INDEX
    Explanations

    Q: questions

    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
     puteți
    -0.90
     kompeti
    -0.89
    OTROS
    -0.85
    ﻡ
    -0.84
     hendes
    -0.81
     kedai
    -0.81
     ideen
    -0.80
    等の
    -0.79
    ＼(^
    -0.79
    しても
    -0.77
    POSITIVE LOGITS
     reformed
    0.98
     Sens
    0.92
    Sens
    0.90
     frontline
    0.88
    Privile
    0.88
    Volumes
    0.87
     Privile
    0.85
     pellet
    0.85
     independent
    0.84
     distribution
    0.83
    Activations Density 0.012%

    No Known Activations