© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9523
    Prev
    Next
    INDEX
    Explanations

    stack and stacking

    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_40_width_16k_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
     aching
    0.40
    える
    0.39
    েশের
    0.39
     nhỉ
    0.38
    achal
    0.38
    ̀nh
    0.37
     ಇನ್ನ
    0.37
    値
    0.37
     বাহিনী
    0.36
     항
    0.36
    POSITIVE LOGITS
     Stack
    0.76
     stack
    0.65
     stacked
    0.61
    栈
    0.59
    Stack
    0.57
     stacks
    0.57
    stacked
    0.57
     stacking
    0.56
     pilha
    0.52
    stack
    0.50
    Activations Density 0.086%

    No Known Activations