© 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. 106896
    Prev
    Next
    INDEX
    Explanations

    measurement and academic writing

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

    a vulnerability: reality is interpreted

    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
     prodotti
    0.55
     cDNA
    0.51
     Şubat
    0.51
     produk
    0.50
     produits
    0.49
     d
    0.48
     Produkte
    0.47
     produktów
    0.47
     prodotto
    0.46
     míst
    0.46
    POSITIVE LOGITS
    ंटी
    0.44
     समार
    0.44
    жете
    0.42
    $=\
    0.41
    ="...">
    0.41
    िरण
    0.41
    ጠቀም
    0.41
    StudentRecord
    0.41
     पेनल
    0.40
    არს
    0.39
    Activations Density 0.001%

    No Known Activations