© 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. 36179
    Prev
    Next
    INDEX
    Explanations

    running replacement niece Exploration

    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
    S
    0.45
    param
    0.43
    T
    0.42
    Q
    0.42
     Cos
    0.41
     monitors
    0.41
     University
    0.40
     observ
    0.40
     monitor
    0.40
     differentiable
    0.40
    POSITIVE LOGITS
    无奈
    0.51
    
    0.49
    య్యా
    0.48
    
    0.46
     сти
    0.45
    ተት
    0.45
    वला
    0.44
    涵盖
    0.44
    ኋላ
    0.44
    <0x04>
    0.44
    Activations Density 0.001%

    No Known Activations