© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7188
    Prev
    Next
    INDEX
    Explanations

    Large language model behaviors

    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_31_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
    ilidade
    0.63
     konnte
    0.53
    }}=\
    0.52
    Ihr
    0.49
    0.47
    Ein
    0.47
     könnte
    0.47
     charakter
    0.46
     préstamo
    0.46
     kunde
    0.45
    POSITIVE LOGITS
     cobalt
    0.54
     blacksmith
    0.52
     Magnesium
    0.48
    циям
    0.47
    蒈
    0.47
     Housing
    0.47
     Cobalt
    0.46
     Lao
    0.46
     Delft
    0.46
     Katie
    0.45
    Activations Density 0.001%

    No Known Activations