© 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. 31-GEMMASCOPE-2-RES-262K
    7. 81969
    Prev
    Next
    INDEX
    Explanations

    machine learning models and algorithms

    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
     Too
    0.45
     всему
    0.43
     مج
    0.42
     Co
    0.41
    ومة
    0.41
    Э
    0.40
     Boyle
    0.40
    壃
    0.40
    ك
    0.39
     বেঁচে
    0.39
    POSITIVE LOGITS
     profite
    0.44
     ekonomik
    0.43
     stylists
    0.42
     handels
    0.41
    economic
    0.41
     {})
    0.41
     onlookers
    0.41
     advisors
    0.41
     evenly
    0.41
     temperaturas
    0.40
    Activations Density 0.002%

    No Known Activations