© 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. 211662
    Prev
    Next
    INDEX
    Explanations

    potential neurotoxic effects

    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
     discrete
    0.40
    淖
    0.39
     Mehr
    0.37
     breakthroughs
    0.37
    aktadır
    0.37
    ურად
    0.36
     simak
    0.36
     సంద
    0.36
     OTC
    0.36
     estreno
    0.35
    POSITIVE LOGITS
    aap
    0.43
    avgsalary
    0.42
     ջ
    0.41
    ᆻ
    0.41
    жений
    0.40
    звичай
    0.39
    লোকের
    0.39
    ắp
    0.38
    蓥
    0.38
    anged
    0.38
    Activations Density 0.001%

    No Known Activations