© 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. 62969
    Prev
    Next
    INDEX
    Explanations

    rescued after being assisted

    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
     mengadakan
    -0.81
     sidewalk
    -0.81
     colonized
    -0.80
     géographie
    -0.79
     massacres
    -0.77
    gerichte
    -0.77
    ṛ
    -0.77
    cinct
    -0.75
     sidewalks
    -0.75
    눌
    -0.75
    POSITIVE LOGITS
     distress
    0.94
     pomocy
    0.92
     abandoned
    0.89
     systému
    0.86
     Gour
    0.85
     coordinates
    0.84
     assistance
    0.81
     vicinity
    0.80
     crew
    0.79
     difficulties
    0.79
    Activations Density 0.018%

    No Known Activations