© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2246
    Prev
    Next
    INDEX
    Explanations

    states like stolen, shortlisted, or symbiotic

    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
     bewusst
    -1.15
    anwalt
    -1.12
     usable
    -1.12
     metav
    -1.11
     largest
    -1.10
    卧槽
    -1.09
    тически
    -1.02
    沢山
    -1.01
    古老
    -1.01
     technology
    -1.00
    POSITIVE LOGITS
     kinda
    1.93
     gotta
    1.89
     dudes
    1.84
    啥
    1.70
     ain
    1.69
    numero
    1.63
     pretty
    1.60
     dude
    1.57
     outta
    1.53
     peeps
    1.53
    Activations Density 0.566%

    No Known Activations