© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166294
    Prev
    Next
    INDEX
    Explanations

    polished finishes

    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
    꺾
    0.40
     potash
    0.39
    反而
    0.39
    盹
    0.38
     असिस्ट
    0.37
    UAGE
    0.37
     pounded
    0.37
    ⏬
    0.36
     yr
    0.36
     찍
    0.36
    POSITIVE LOGITS
    veren
    0.42
    Enfin
    0.38
     indicadores
    0.38
    coons
    0.38
    Sonar
    0.38
     पहलुओं
    0.37
     salivary
    0.37
     મહત્વ
    0.37
    Details
    0.37
     conjectures
    0.37
    Activations Density 0.000%

    No Known Activations