© 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. 15936
    Prev
    Next
    INDEX
    Explanations

    data structures and classes

    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
     unsightly
    0.43
     writs
    0.39
     tomato
    0.38
     thumb
    0.36
    脚注
    0.36
    妘
    0.36
    桕
    0.35
     Worte
    0.35
    詓
    0.35
     setImage
    0.35
    POSITIVE LOGITS
    based
    0.52
    El
    0.49
    3
    0.45
    target
    0.42
    help
    0.41
    helps
    0.40
    create
    0.40
    start
    0.40
    define
    0.40
    ample
    0.39
    Activations Density 0.171%

    No Known Activations