© 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. 31-GEMMASCOPE-2-RES-65K
    7. 53329
    Prev
    Next
    INDEX
    Explanations

    date of birth

    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_65k_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
    ية
    0.48
     apare
    0.47
     Token
    0.47
     zásobníku
    0.47
     Filtering
    0.47
     að
    0.47
    д
    0.46
    obs
    0.46
     absurd
    0.45
     Gray
    0.45
    POSITIVE LOGITS
     आवाहन
    0.47
    m
    0.46
    捏
    0.45
     mummy
    0.43
     confidentiality
    0.42
     congressman
    0.42
    ACH
    0.41
    Came
    0.41
    chloride
    0.41
    نع
    0.40
    Activations Density 0.005%

    No Known Activations