© 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-16K
    7. 583
    Prev
    Next
    INDEX
    Explanations

    parts of phrases

    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_16k_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
     (
    0.43
    0.40
     {
    0.39
     Gaussian
    0.38
     a
    0.37
     Container
    0.37
     \
    0.36
     handheld
    0.35
     automatisch
    0.34
     Scope
    0.33
    POSITIVE LOGITS
    ра
    0.46
    ের
    0.45
    ترین
    0.45
    ی
    0.44
    ostante
    0.42
    е
    0.41
    པ
    0.41
    ка
    0.40
    誠
    0.39
    ने
    0.39
    Activations Density 0.025%

    No Known Activations