© 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. 108779
    Prev
    Next
    INDEX
    Explanations

    rel attributes

    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
    🍘
    -0.82
    rams
    -0.74
     RURAL
    -0.72
     nobleman
    -0.71
    govor
    -0.70
    케
    -0.70
    рот
    -0.69
     zoon
    -0.69
    燗
    -0.69
    Nin
    -0.68
    POSITIVE LOGITS
     rel
    3.00
    rel
    2.55
     Rel
    2.17
    Rel
    1.96
     REL
    1.77
    REL
    1.66
     relations
    1.45
     relation
    1.44
     relativistic
    1.38
    rels
    1.32
    Activations Density 0.136%

    No Known Activations