© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132473
    Prev
    Next
    INDEX
    Explanations

    visual inspection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     públicas
    0.46
     වල
    0.42
     larc
    0.42
     necks
    0.41
    股份
    0.41
     Italy
    0.39
    혀
    0.39
     larges
    0.39
    بير
    0.38
    룹
    0.38
    POSITIVE LOGITS
     подготовки
    0.41
    Daten
    0.40
    irla
    0.40
    Unsere
    0.39
    proposition
    0.37
     bieten
    0.37
    Proposition
    0.36
    ែម
    0.35
    freien
    0.34
    Gab
    0.34
    Activations Density 0.000%

    No Known Activations