© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109625
    Prev
    Next
    INDEX
    Explanations

    thebetweenlands blocks

    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
     Ama
    -0.74
    Arduino
    -0.71
     gazed
    -0.70
    issier
    -0.68
    Alexandra
    -0.67
    ⊇
    -0.66
     orc
    -0.66
     EC
    -0.66
    Associate
    -0.65
     superheroes
    -0.65
    POSITIVE LOGITS
    anjutan
    0.82
     "".
    0.80
    mico
    0.77
    饥
    0.77
     DOE
    0.76
    ⍣
    0.75
    ilig
    0.72
     podrob
    0.70
    tanie
    0.70
     Qualitäts
    0.69
    Activations Density 0.012%

    No Known Activations