© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59536
    Prev
    Next
    INDEX
    Explanations

    safety, houses, damage,excellence

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

    playful and curiosity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    에
    0.46
     heartache
    0.44
    ஞ்ச
    0.43
    は
    0.42
     assaulting
    0.41
     figurative
    0.41
    Objective
    0.41
    ガチャ
    0.40
    с
    0.40
     assault
    0.40
    POSITIVE LOGITS
     美国
    0.55
    ޘ
    0.54
     儿童
    0.52
     thrived
    0.48
     要求
    0.47
    తంగా
    0.47
     如果
    0.46
     థ
    0.46
    稃
    0.46
    ন্ত্র
    0.45
    Activations Density 0.000%

    No Known Activations