© 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. 193670
    Prev
    Next
    INDEX
    Explanations

    Erz, Eritrea, Ram, Vehicle

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

    finding what follows a key word

    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
    出
    0.55
    一
    0.54
    жными
    0.49
    闇
    0.47
    아
    0.47
    एक
    0.47
    दर
    0.46
    бно
    0.46
    灵
    0.46
    엄
    0.46
    POSITIVE LOGITS
     Erz
    0.62
     Eritrea
    0.62
     Ram
    0.59
     Vehicle
    0.58
     Bon
    0.55
     Kil
    0.54
     Rhin
    0.53
     Aye
    0.52
     Som
    0.52
     Toy
    0.52
    Activations Density 0.000%

    No Known Activations