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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4822
    Prev
    Next
    INDEX
    Explanations

    JSON structure keys

    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
     National
    0.37
    cdnjs
    0.36
    ্
    0.36
    amsmath
    0.35
     Nasional
    0.35
    ak
    0.34
     Republic
    0.34
    idan
    0.33
    ?
    0.33
    street
    0.33
    POSITIVE LOGITS
     metaphys
    0.41
    Defining
    0.41
     thinker
    0.41
    ैमर
    0.41
    Description
    0.41
     armazen
    0.40
     usos
    0.40
     voll
    0.40
    ূর্ন
    0.39
     entstanden
    0.39
    Activations Density 0.092%

    No Known Activations