© 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. 142910
    Prev
    Next
    INDEX
    Explanations

    country names and specific organizations

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

    Creates or maintains

    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
    자를
    0.49
    密
    0.48
    రో
    0.46
    োপ
    0.43
    జ్
    0.43
    ज्ज
    0.42
    лят
    0.41
    ايا
    0.41
    密集
    0.40
    йдз
    0.40
    POSITIVE LOGITS
     मटेरियल
    0.50
     ولی
    0.49
     ข้าง
    0.48
     cytologic
    0.48
     edits
    0.48
     avoir
    0.47
     believing
    0.47
    𝑖
    0.47
     کیونکہ
    0.47
     terreno
    0.46
    Activations Density 0.000%

    No Known Activations