© 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. 170101
    Prev
    Next
    INDEX
    Explanations

    distressed dining room

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

    autoencoder, primes, Session, DIY

    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
     Sabemos
    0.45
     cooperating
    0.43
     querying
    0.42
     Sellers
    0.42
     gerçekten
    0.42
    难
    0.42
     Szk
    0.41
    ২৯
    0.41
     privilégi
    0.41
    фициа
    0.41
    POSITIVE LOGITS
     histograms
    0.46
     fis
    0.43
    ixon
    0.43
     remnants
    0.43
    𝗢
    0.43
    Or
    0.42
     descriptors
    0.42
     inclinations
    0.41
                
    0.41
    oles
    0.41
    Activations Density 0.001%

    No Known Activations