© 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. 40-GEMMASCOPE-2-RES-262K
    7. 984
    Prev
    Next
    INDEX
    Explanations

    Spanish greetings and nationalist groups

    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_40_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
     \\
    0.40
     suces
    0.39
    લું
    0.38
    <u>
    0.37
     lh
    0.37
     zab
    0.36
    \'
    0.36
    &#
    0.35
    Kc
    0.35
     \&
    0.35
    POSITIVE LOGITS
    ettiva
    0.47
     decirle
    0.47
    িয়ার
    0.46
    利亚
    0.45
    企业家
    0.44
     Absolutely
    0.42
    醫師
    0.42
    情的
    0.42
     субъек
    0.41
     Vantage
    0.41
    Activations Density 0.000%

    No Known Activations