© 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. 12171
    Prev
    Next
    INDEX
    Explanations

    any even tiny

    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
     ながら
    0.41
    گیز
    0.38
     সম্ভবত
    0.37
    之所以
    0.37
     zwar
    0.37
    بیه
    0.36
    addObject
    0.36
    㤓
    0.36
     Plenty
    0.35
     Possibly
    0.34
    POSITIVE LOGITS
     slightest
    1.98
    哪怕
    1.66
     even
    1.52
     tini
    1.49
     даже
    1.46
    even
    1.37
     smallest
    1.34
     حتی
    1.30
     навіть
    1.30
     EVEN
    1.25
    Activations Density 0.038%

    No Known Activations