© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48020
    Prev
    Next
    INDEX
    Explanations

    attacker information Jewish Harry deception

    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_31_width_65k_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
     sociais
    0.55
     árv
    0.54
     божомолдор
    0.52
    Customize
    0.52
    ㄾ
    0.52
     ženy
    0.51
    <%@
    0.50
    粔
    0.49
    〢
    0.49
     atualizar
    0.48
    POSITIVE LOGITS
    ↵↵↵
    0.43
     en
    0.42
     on
    0.42
     Harry
    0.42
    ↵↵
    0.42
     deception
    0.41
     Companion
    0.41
    纳米
    0.40
     A
    0.39
     Cas
    0.39
    Activations Density 0.004%

    No Known Activations