© 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. 4716
    Prev
    Next
    INDEX
    Explanations

    price index and metrics

    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
    5
    0.50
    ()),
    0.46
    6
    0.41
    V
    0.39
    l
    0.39
     management
    0.38
     Origin
    0.38
    veget
    0.38
     prosecuting
    0.38
    7
    0.37
    POSITIVE LOGITS
    チャート
    0.51
    ียม
    0.45
     крайне
    0.45
    িলাম
    0.44
     Daniele
    0.43
    츨
    0.43
    我覺得
    0.42
     tenuous
    0.42
     amplio
    0.42
     многим
    0.42
    Activations Density 0.008%

    No Known Activations