© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 106871
    Prev
    Next
    INDEX
    Explanations

    any set

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

    telling you what i want

    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
    的重要
    0.47
    每个人
    0.43
    如果您
    0.43
    б
    0.43
    Б
    0.43
    令人
    0.41
    视野
    0.41
    បន្ថែម
    0.40
    🆈
    0.40
    Fala
    0.40
    POSITIVE LOGITS
    ٹو
    0.49
    i
    0.48
     گرفتار
    0.45
    aży
    0.45
     پہ
    0.44
     partitioning
    0.44
    殲
    0.43
     গ্রহ
    0.43
     取り
    0.43
     موز
    0.43
    Activations Density 0.001%

    No Known Activations