© 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. 139684
    Prev
    Next
    INDEX
    Explanations

    foreign words and economic terms

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

    individual circumstances and viewpoints

    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
     Turnier
    0.47
    commande
    0.45
     Gymn
    0.45
    o
    0.44
    étrico
    0.43
    第
    0.42
    拉
    0.42
     gymnast
    0.42
     संघटना
    0.42
    oría
    0.42
    POSITIVE LOGITS
     bes
    0.47
    ಿವ
    0.43
    moved
    0.42
     pence
    0.42
     nabíd
    0.41
     zwró
    0.41
     moved
    0.40
     downturn
    0.40
    }}_
    0.40
    MF
    0.40
    Activations Density 0.001%

    No Known Activations