© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66757
    Prev
    Next
    INDEX
    Explanations

    MA: UpToDate citations

    np_acts-logits-general · gemini-2.5-flash-lite

    extremely careful vetting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zeitpunkt
    0.48
    ).
    0.47
     Fron
    0.44
    ве
    0.44
     Subtle
    0.43
     Tissue
    0.43
    ่
    0.42
    का
    0.42
     Neuron
    0.42
     simultaneously
    0.41
    POSITIVE LOGITS
     упомина
    0.59
    ego
    0.52
     посла
    0.48
    タック
    0.47
    engin
    0.46
    ura
    0.44
     promiscu
    0.43
     পড়েছে
    0.43
    golden
    0.42
    esistenza
    0.42
    Activations Density 0.000%

    No Known Activations