© 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. 146118
    Prev
    Next
    INDEX
    Explanations

    currency rates, Christ, before, below

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

    existence and reality

    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
     extrem
    0.44
     kaisi
    0.44
     differentiator
    0.44
     одним
    0.44
    ffler
    0.42
     corrected
    0.42
    ็บ
    0.41
    .";
    0.41
     shootout
    0.40
     way
    0.40
    POSITIVE LOGITS
     অংশগ্রহণ
    0.47
     biota
    0.44
     sedent
    0.44
     অবস্থিত
    0.43
    ძლიათ
    0.43
     অনুষ্ঠিত
    0.43
     Sediment
    0.43
     স্থাপন
    0.42
    addSub
    0.42
     সন্
    0.41
    Activations Density 0.000%

    No Known Activations