© 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. 80777
    Prev
    Next
    INDEX
    Explanations

    closings and names

    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
    𝙉
    -0.97
    ஃ
    -0.88
     SPEC
    -0.85
     allerlei
    -0.85
    ஹ
    -0.82
    ikr
    -0.82
    MLP
    -0.80
    Strategies
    -0.80
     لكن
    -0.80
     België
    -0.80
    POSITIVE LOGITS
     regards
    1.64
     Regards
    1.34
    regards
    1.33
    Regards
    1.20
     Jim
    1.09
    jim
    1.01
    JIM
    1.00
    Jim
    1.00
    ífer
    0.99
     cheers
    0.98
    Activations Density 0.032%

    No Known Activations