© 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. 94031
    Prev
    Next
    INDEX
    Explanations

    spin-off

    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
    LOADED
    -0.70
     embassy
    -0.69
     juxtaposition
    -0.69
     Parmi
    -0.67
     permesso
    -0.65
    estal
    -0.65
    范文
    -0.64
    ემ
    -0.64
     typos
    -0.64
     immersion
    -0.64
    POSITIVE LOGITS
     spin
    6.06
    spin
    4.81
    Spin
    4.25
     Spin
    4.09
     spun
    3.47
     SPIN
    3.39
    SPIN
    3.30
     spins
    3.28
     spinning
    3.20
    スピ
    2.72
    Activations Density 0.078%

    No Known Activations