© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6888
    Prev
    Next
    INDEX
    Explanations

    seeking advice or stating purpose

    np_acts-logits-general · gemini-2.5-flash-lite

    semantically salient content words—especially technical terms, action verbs, and key connectors—that carry the main informational load of a sentence.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    
    0.20
     titleImageUrl
    0.20
     abstr
    0.19
     enteros
    0.18
     overfitting
    0.18
     hierarch
    0.18
     melan
    0.17
     obscur
    0.17
     ridiculus
    0.17
    🦐
    0.17
    POSITIVE LOGITS
    0.25
     I
    0.21
    з
    0.20
    ada
    0.19
     be
    0.18
    蓣
    0.18
     UAE
    0.18
     Cricket
    0.18
    ing
    0.18
    での
    0.18
    Activations Density 1.101%

    No Known Activations