© 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. 187685
    Prev
    Next
    INDEX
    Explanations

    people's names

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

    pi, crypto, money, respectful, suggestive

    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
     knowing
    0.46
    
    0.44
     recours
    0.42
     calibrated
    0.42
    하고
    0.41
     penchant
    0.41
    преде
    0.41
     categorized
    0.41
    ≥</
    0.41
    ஊ
    0.40
    POSITIVE LOGITS
    rocery
    0.50
     abo
    0.47
     Mujeres
    0.46
     сообщил
    0.46
     hous
    0.45
    ంగ్
    0.45
     жен
    0.44
     (~
    0.44
    ষি
    0.44
     ampli
    0.43
    Activations Density 0.002%

    No Known Activations