© 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. 40-GEMMASCOPE-2-RES-262K
    7. 109719
    Prev
    Next
    INDEX
    Explanations

    legal weights and measures

    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_40_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
    洄
    0.38
    ल्
    0.38
     परिचाल
    0.37
    льта
    0.36
     Screenshots
    0.36
     aggregate
    0.36
     fatig
    0.36
     ധ
    0.35
     शाखा
    0.35
    ھیں
    0.35
    POSITIVE LOGITS
     weights
    1.57
     Weights
    1.51
    Weights
    1.42
    weights
    1.35
     measurement
    1.30
     Measurement
    1.27
    Measurement
    1.24
    measurement
    1.23
     standardization
    1.16
     measurements
    1.13
    Activations Density 0.017%

    No Known Activations