© 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. 66150
    Prev
    Next
    INDEX
    Explanations

    legal claims and procedures

    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
     näky
    -1.17
     altid
    -1.00
     suuri
    -0.99
     certiorari
    -0.98
     détach
    -0.98
     erstat
    -0.98
     OKAY
    -0.96
     ſal
    -0.94
     NLRB
    -0.94
     nadar
    -0.92
    POSITIVE LOGITS
     question
    1.62
     only
    1.58
     position
    1.45
     circumstances
    1.38
     finding
    1.38
     correct
    1.37
     matter
    1.28
     second
    1.27
     effect
    1.27
     evidence
    1.25
    Activations Density 0.009%

    No Known Activations