© 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. 37089
    Prev
    Next
    INDEX
    Explanations

    Closest distance

    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
    k
    0.52
    g
    0.49
    fourth
    0.49
    t
    0.46
    p
    0.45
    fishing
    0.45
    x
    0.45
     manslaughter
    0.44
    m
    0.44
    c
    0.44
    POSITIVE LOGITS
     Udemy
    0.50
    enza
    0.47
     ages
    0.47
    ogat
    0.47
     Strategic
    0.44
     unlock
    0.43
     وهم
    0.43
    ципа
    0.43
    età
    0.42
    ето
    0.42
    Activations Density 0.001%

    No Known Activations