© 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. 70501
    Prev
    Next
    INDEX
    Explanations

    certificates and copies

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

    even followed by consequence

    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
     κοινων
    0.47
     Increasingly
    0.46
     服务
    0.45
     周
    0.45
     আসছেন
    0.42
     পারছেন
    0.42
     sosyal
    0.41
     khách
    0.41
     социальной
    0.41
     championed
    0.41
    POSITIVE LOGITS
     erwäh
    0.46
     vérit
    0.43
     velocità
    0.42
     régl
    0.41
     MHz
    0.40
     curing
    0.40
    T
    0.40
     menjal
    0.40
    ுத
    0.40
     overdrive
    0.40
    Activations Density 0.000%

    No Known Activations