© 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. 154304
    Prev
    Next
    INDEX
    Explanations

    family members and belongings

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

    its potential

    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
    ί
    0.47
    开始
    0.46
    してきた
    0.46
    describe
    0.45
    ってきた
    0.44
    atangan
    0.43
    мпаваць
    0.42
    ικό
    0.41
    拖
    0.40
    already
    0.40
    POSITIVE LOGITS
     مدر
    0.57
    受け
    0.49
    קה
    0.43
    hette
    0.42
    SecurityMarks
    0.42
    ቁ
    0.42
    峮
    0.41
     ذریع
    0.41
    聡
    0.41
    ソース
    0.40
    Activations Density 0.000%

    No Known Activations