© 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-262K
    7. 28144
    Prev
    Next
    INDEX
    Explanations

    keto diet, awards, latent, ion, elk, white

    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
     Nitrogen
    0.46
    辮
    0.45
     OSError
    0.44
     Epidemiology
    0.44
    विधि
    0.44
     Data
    0.44
     explain
    0.43
     wcześ
    0.42
    ৫
    0.42
    安全的
    0.42
    POSITIVE LOGITS
     и
    0.44
     आणि
    0.44
    、
    0.44
    дина
    0.42
     стали
    0.42
     имуще
    0.42
     மற்றும்
    0.41
     financiero
    0.40
     α
    0.40
     им
    0.39
    Activations Density 0.001%

    No Known Activations