© 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. 1653
    Prev
    Next
    INDEX
    Explanations

    through

    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
    ি
    0.74
    ை
    0.66
    ே
    0.64
    i
    0.63
    iagn
    0.62
     ""`
    0.57
    ко
    0.57
    u
    0.57
    ik
    0.57
    ാ
    0.55
    POSITIVE LOGITS
     through
    1.12
    通过
    0.94
     через
    0.94
     melalui
    0.93
     através
    0.92
     durch
    0.90
     kroz
    0.88
     través
    0.84
    Through
    0.81
     Through
    0.79
    Activations Density 0.059%

    No Known Activations