© 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. 50008
    Prev
    Next
    INDEX
    Explanations

    charter members, $ amounts, shock absorbers

    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
     treason
    -0.86
    textAlignment
    -0.85
    aris
    -0.80
    EXPORT
    -0.78
     cso
    -0.78
     translators
    -0.78
     Unwin
    -0.77
     Trimble
    -0.77
    lator
    -0.74
    ISTE
    -0.74
    POSITIVE LOGITS
     pledge
    2.41
     initiation
    2.31
     pledges
    2.17
     pledging
    2.00
     Initiation
    1.92
    pled
    1.85
     pledged
    1.72
     Pledge
    1.65
    Initi
    1.49
     initiates
    1.45
    Activations Density 0.015%

    No Known Activations