© 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. 128516
    Prev
    Next
    INDEX
    Explanations

    limited, maximum, cost, chasing, christmas

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

    computer memory

    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
    湾
    0.50
     Projet
    0.47
     New
    0.46
    u
    0.46
    ெல்ல
    0.46
    灣
    0.46
     Request
    0.45
    Trust
    0.44
     Making
    0.43
    이지만
    0.43
    POSITIVE LOGITS
    slideDuplicate
    0.57
     affez
    0.48
    ￢
    0.48
     afectada
    0.48
     שכ
    0.47
     enig
    0.46
    profitLoss
    0.46
    /=
    0.46
    /*'
    0.45
    Affected
    0.45
    Activations Density 0.000%

    No Known Activations