© 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. 136265
    Prev
    Next
    INDEX
    Explanations

    stage, Coaching, or following prepositions

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

    operating between operands

    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
    服务
    0.43
     veröffent
    0.43
    ధ
    0.42
    䜣
    0.42
    檔案
    0.42
    ิศ
    0.41
     tjän
    0.41
    关闭
    0.41
     publicada
    0.41
    磵
    0.40
    POSITIVE LOGITS
     Ке
    0.53
     受け
    0.49
    sear
    0.48
     Hero
    0.47
     ชาว
    0.47
     Chaotic
    0.46
     Heroes
    0.45
     Patri
    0.44
    teau
    0.44
     Chiefs
    0.44
    Activations Density 0.000%

    No Known Activations