© 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. 31018
    Prev
    Next
    INDEX
    Explanations

    people and roles alike

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

    various groups seeking something

    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
    business
    0.46
    आप
    0.46
    params
    0.46
    proteins
    0.46
    member
    0.45
    some
    0.43
    norm
    0.43
    被
    0.43
    activity
    0.43
    hour
    0.43
    POSITIVE LOGITS
     alike
    0.82
     wanting
    0.57
     seeking
    0.52
     everywhere
    0.51
     בכל
    0.50
     onlookers
    0.50
     galore
    0.48
    一样
    0.47
    alike
    0.47
     eyeing
    0.47
    Activations Density 0.066%

    No Known Activations