© 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. 11844
    Prev
    Next
    INDEX
    Explanations

    private code declarations

    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
    the
    0.55
    ISH
    0.48
     Models
    0.47
     Mudah
    0.46
     Sehen
    0.46
    okka
    0.46
     //{
    0.45
     Lihat
    0.45
    ICK
    0.45
     Recommend
    0.45
    POSITIVE LOGITS
     ayahuasca
    0.58
     hitters
    0.56
     incessant
    0.54
     duvet
    0.52
     cramping
    0.52
     grouse
    0.52
     déjà
    0.50
     약
    0.49
     nylon
    0.49
     hazy
    0.49
    Activations Density 0.015%

    No Known Activations