© 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. 86756
    Prev
    Next
    INDEX
    Explanations

    starts with Modern, Ultra, Financial

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

    personal responsibility, colic, chemotherapy

    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
    其中包括
    0.48
     '\\;'
    0.46
    包括
    0.43
     ಅವ
    0.41
     בג
    0.41
     WITHOUT
    0.41
     包括
    0.40
     muzy
    0.39
    咟
    0.39
    𒁺
    0.39
    POSITIVE LOGITS
     elixir
    0.43
    อีก
    0.41
    絶対
    0.41
     another
    0.40
    another
    0.40
     Reddy
    0.39
    きっと
    0.38
     monsoon
    0.38
    <u>
    0.38
     lining
    0.38
    Activations Density 0.000%

    No Known Activations