© 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. 83720
    Prev
    Next
    INDEX
    Explanations

    steps down or up

    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
     LOCKED
    0.43
    ⊇
    0.41
    пах
    0.40
    
    0.40
     διάρκ
    0.39
     referencia
    0.38
     গাড়ী
    0.37
     sized
    0.37
    ocor
    0.36
     ilustración
    0.36
    POSITIVE LOGITS
     Provincial
    0.39
     elevate
    0.39
    coerce
    0.38
     cript
    0.38
     Amb
    0.38
     crist
    0.38
    }^{+}+
    0.38
    ՞
    0.37
     leather
    0.37
    Elev
    0.37
    Activations Density 0.001%

    No Known Activations