© 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. 20965
    Prev
    Next
    INDEX
    Explanations

    financial numbers and organizations

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

    market capitalization statistics

    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
    anmoins
    0.45
     overriding
    0.44
     smo
    0.43
    ベー
    0.43
    .,
    0.42
     ቀ
    0.41
     ado
    0.41
     過
    0.41
     温度
    0.39
    細かい
    0.39
    POSITIVE LOGITS
     সঞ্জীবনী
    0.44
    рим
    0.39
     سیاست
    0.38
    醮
    0.38
    OECD
    0.36
     Caen
    0.36
    currentChar
    0.36
     zinc
    0.35
    ائرة
    0.35
     православ
    0.34
    Activations Density 0.003%

    No Known Activations