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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20113
    Prev
    Next
    INDEX
    Explanations

    hallucinate facts

    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_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
     elites
    0.50
     defaul
    0.49
    Ꮡ
    0.47
     vittime
    0.47
     cannons
    0.46
     garam
    0.46
     alé
    0.46
     naturelle
    0.46
     rehab
    0.44
     capitalists
    0.44
    POSITIVE LOGITS
    也就是说
    0.53
    urgical
    0.49
    the
    0.48
    时间
    0.46
    <0x80>
    0.44
    ]
    0.44
    ual
    0.43
    chdir
    0.43
     प्रकाश
    0.43
     设置
    0.43
    Activations Density 0.001%

    No Known Activations