© 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-262K
    7. 1900
    Prev
    Next
    INDEX
    Explanations

    addition of numbers and symbols

    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_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
    decreasing
    0.50
    ominus
    0.41
    ായിരുന്നു
    0.40
    েবের
    0.40
     $-
    0.40
    Minus
    0.40
    娍
    0.39
    walled
    0.39
    othelium
    0.38
    काया
    0.38
    POSITIVE LOGITS
     +
    2.02
     plus
    1.65
     плюс
    1.61
    +
    1.59
    加上
    1.55
     $+$
    1.50
     ditambah
    1.49
    ()+
    1.45
    再加上
    1.45
    ＋
    1.45
    Activations Density 0.078%

    No Known Activations