© 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. 43925
    Prev
    Next
    INDEX
    Explanations

    civil engineering, classic cars

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

    activities and technical concepts

    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
    卢
    0.59
    라마
    0.58
    荣
    0.54
    Ր
    0.52
    сон
    0.51
    STRUCTION
    0.51
     лучших
    0.50
    मै
    0.50
    َق
    0.50
    SING
    0.50
    POSITIVE LOGITS
    ile
    0.53
    eter
    0.53
    s
    0.52
    rip
    0.50
     held
    0.49
    both
    0.48
    pa
    0.46
     sediment
    0.46
    iel
    0.46
     both
    0.46
    Activations Density 0.000%

    No Known Activations