© 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. 16-GEMMASCOPE-2-RES-262K
    7. 46276
    Prev
    Next
    INDEX
    Explanations

    sydney fc

    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_16_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
    _
    0.67
    en
    0.65
    的同时
    0.64
    ów
    0.63
     отлича
    0.60
    )},
    0.57
    )}+\
    0.57
    得以
    0.57
     de
    0.55
     atmosphere
    0.55
    POSITIVE LOGITS
    s
    1.12
    ی
    1.02
    ﺝ
    0.90
    ㍉
    0.86
    ﺍ
    0.85
    است
    0.84
    weights
    0.81
    t
    0.80
    ス
    0.80
     muon
    0.79
    Activations Density 0.001%

    No Known Activations