© 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. 95134
    Prev
    Next
    INDEX
    Explanations

    rose, meaning

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

    formal, often, carries, respect

    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
    atge
    0.47
     puedas
    0.47
     The
    0.44
     بتوان
    0.43
    <unused2121>
    0.42
     Hackney
    0.41
     aplicativo
    0.41
     utilizar
    0.41
     finalidad
    0.41
     Bayes
    0.40
    POSITIVE LOGITS
     chargé
    0.47
    赈
    0.46
     책임
    0.45
     기억
    0.45
    irmer
    0.44
    攥
    0.43
    惋
    0.42
     rousing
    0.42
     sobbing
    0.42
    ภาษ
    0.42
    Activations Density 0.000%

    No Known Activations