© 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. 1742
    Prev
    Next
    INDEX
    Explanations

    want or seek something

    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
    X
    0.31
    ww
    0.28
    w
    0.27
    c
    0.27
    x
    0.27
    at
    0.27
    k
    0.26
     protruding
    0.26
    ()>
    0.26
                        
    0.25
    POSITIVE LOGITS
     aiuto
    0.42
     desperately
    0.35
     toegang
    0.35
     nourriture
    0.34
     trouver
    0.33
     help
    0.33
     ayuda
    0.33
     sostegno
    0.32
     ajuda
    0.32
     trovare
    0.32
    Activations Density 0.317%

    No Known Activations