© 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. 227695
    Prev
    Next
    INDEX
    Explanations

    super man, reefs everywhere, personnel scrub

    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
    مث
    0.53
    ために
    0.50
    랙
    0.50
    ニチイ
    0.49
    iffy
    0.49
    ت
    0.48
    ᐋ
    0.48
    पन
    0.47
    谅
    0.47
    Wayne
    0.46
    POSITIVE LOGITS
     immobilized
    0.53
     Palma
    0.53
     wrinkled
    0.50
     fled
    0.50
     sunscreen
    0.49
     Kar
    0.47
     fleeing
    0.47
     Cath
    0.46
     crucified
    0.45
     stripped
    0.45
    Activations Density 0.001%

    No Known Activations