© 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-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47944
    Prev
    Next
    INDEX
    Explanations

    specifics and science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     i
    0.46
     mogelijk
    0.45
     nhưng
    0.44
     находится
    0.43
     ហើយ
    0.42
     progetto
    0.41
     create
    0.40
     आता
    0.40
     अर्थात
    0.40
     stylesheet
    0.40
    POSITIVE LOGITS
    вах
    0.46
     پیغم
    0.44
    тической
    0.43
    纤维
    0.43
    沾
    0.43
     Guardians
    0.42
    нави
    0.42
     موب
    0.41
     Fibre
    0.41
    抗菌
    0.41
    Activations Density 0.002%

    No Known Activations