© 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. 148914
    Prev
    Next
    INDEX
    Explanations

    cook this

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

    writing safe stories

    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
    䳕
    0.52
    чення
    0.45
     reducción
    0.45
     मजदूरों
    0.43
    asının
    0.43
    ım
    0.43
    يمان
    0.42
    缓冲
    0.42
    нено
    0.41
     Soldier
    0.41
    POSITIVE LOGITS
    Μ
    0.54
    Мо
    0.52
    Фу
    0.49
     esclus
    0.49
    Бо
    0.49
    Ма
    0.47
    که
    0.47
    𝐌
    0.47
    До
    0.47
    Т
    0.47
    Activations Density 0.000%

    No Known Activations